Artykuły w czasopismach na temat „Compositional generalization”
Kliknij ten link, aby zobaczyć inne rodzaje publikacji na ten temat: Compositional generalization.
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych artykułów w czasopismach naukowych na temat „Compositional generalization”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj artykuły w czasopismach z różnych dziedzin i twórz odpowiednie bibliografie.
1
Chai, Yuyang, Zhuang Li, Jiahui Liu, Lei Chen, Fei Li, Donghong Ji i Chong Teng. "Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach". Proceedings of the AAAI Conference on Artificial Intelligence 38, nr 16 (24.03.2024): 17727–35. http://dx.doi.org/10.1609/aaai.v38i16.29725.
Pełny tekst źródłaStreszczenie:
Despite significant advancements in multi-label text classification, the ability of existing models to generalize to novel and seldom-encountered complex concepts, which are compositions of elementary ones, remains underexplored. This research addresses this gap. By creating unique data splits across three benchmarks, we assess the compositional generalization ability of existing multi-label text classification models. Our results show that these models often fail to generalize to compositional concepts encountered infrequently during training, leading to inferior performance on tests with these new combinations. To address this, we introduce a data augmentation method that leverages two innovative text generation models designed to enhance the classification models' capacity for compositional generalization. Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines. Our codes available at https://github.com/yychai74/LD-VAE.
2
Baroni, Marco. "Linguistic generalization and compositionality in modern artificial neural networks". Philosophical Transactions of the Royal Society B: Biological Sciences 375, nr 1791 (16.12.2019): 20190307. http://dx.doi.org/10.1098/rstb.2019.0307.
Pełny tekst źródłaStreszczenie:
In the last decade, deep artificial neural networks have achieved astounding performance in many natural language-processing tasks. Given the high productivity of language, these models must possess effective generalization abilities. It is widely assumed that humans handle linguistic productivity by means of algebraic compositional rules: are deep networks similarly compositional? After reviewing the main innovations characterizing current deep language-processing networks, I discuss a set of studies suggesting that deep networks are capable of subtle grammar-dependent generalizations, but also that they do not rely on systematic compositional rules. I argue that the intriguing behaviour of these devices (still awaiting a full understanding) should be of interest to linguists and cognitive scientists, as it offers a new perspective on possible computational strategies to deal with linguistic productivity beyond rule-based compositionality, and it might lead to new insights into the less systematic generalization patterns that also appear in natural language. This article is part of the theme issue ‘Towards mechanistic models of meaning composition’.
3
Zheng, Yafang, Lei Lin, Shuangtao Li, Yuxuan Yuan, Zhaohong Lai, Shan Liu, Biao Fu, Yidong Chen i Xiaodong Shi. "Layer-Wise Representation Fusion for Compositional Generalization". Proceedings of the AAAI Conference on Artificial Intelligence 38, nr 17 (24.03.2024): 19706–14. http://dx.doi.org/10.1609/aaai.v38i17.29944.
Pełny tekst źródłaStreszczenie:
Existing neural models are demonstrated to struggle with compositional generalization (CG), i.e., the ability to systematically generalize to unseen compositions of seen components. A key reason for failure on CG is that the syntactic and semantic representations of sequences in both the uppermost layer of the encoder and decoder are entangled. However, previous work concentrates on separating the learning of syntax and semantics instead of exploring the reasons behind the representation entanglement (RE) problem to solve it. We explain why it exists by analyzing the representation evolving mechanism from the bottom to the top of the Transformer layers. We find that the ``shallow'' residual connections within each layer fail to fuse previous layers' information effectively, leading to information forgetting between layers and further the RE problems. Inspired by this, we propose LRF, a novel Layer-wise Representation Fusion framework for CG, which learns to fuse previous layers' information back into the encoding and decoding process effectively through introducing a fuse-attention module at each encoder and decoder layer. LRF achieves promising results on two realistic benchmarks, empirically demonstrating the effectiveness of our proposal. Codes are available at https://github.com/thinkaboutzero/LRF.
4
Kim, Segwang, Joonyoung Kim i Kyomin Jung. "Compositional Generalization via Parsing Tree Annotation". IEEE Access 9 (2021): 24326–33. http://dx.doi.org/10.1109/access.2021.3055513.
Pełny tekst źródła
5
Liu, Xinpeng, Yong-Lu Li i Cewu Lu. "Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection". Proceedings of the AAAI Conference on Artificial Intelligence 36, nr 2 (28.06.2022): 1819–27. http://dx.doi.org/10.1609/aaai.v36i2.20075.
Pełny tekst źródłaStreszczenie:
Human-Object Interaction (HOI) detection plays a core role in activity understanding. As a compositional learning problem (human-verb-object), studying its generalization matters. However, widely-used metric mean average precision (mAP) fails to model the compositional generalization well. Thus, we propose a novel metric, mPD (mean Performance Degradation), as a complementary of mAP to evaluate the performance gap among compositions of different objects and the same verb. Surprisingly, mPD reveals that previous methods usually generalize poorly. With mPD as a cue, we propose Object Category (OC) Immunity to boost HOI generalization. The idea is to prevent model from learning spurious object-verb correlations as a short-cut to over-fit the train set. To achieve OC-immunity, we propose an OC-immune network that decouples the inputs from OC, extracts OC-immune representations, and leverages uncertainty quantification to generalize to unseen objects. In both conventional and zero-shot experiments, our method achieves decent improvements. To fully evaluate the generalization, we design a new and more difficult benchmark, on which we present significant advantage. The code is available at https://github.com/Foruck/OC-Immunity.
6
Jing, Chenchen, Yukun Li, Hao Chen i Chunhua Shen. "Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning". Proceedings of the AAAI Conference on Artificial Intelligence 38, nr 3 (24.03.2024): 2652–60. http://dx.doi.org/10.1609/aaai.v38i3.28043.
Pełny tekst źródłaStreszczenie:
Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by learning from seen compositions. Composing the learned knowledge of seen primitives, i.e., attributes or objects, into novel compositions is critical for CZSL. In this work, we propose to explicitly retrieve knowledge of seen primitives for compositional zero-shot learning. We present a retrieval-augmented method, which augments standard multi-path classification methods with two retrieval modules. Specifically, we construct two databases storing the attribute and object representations of training images, respectively. For an input training/testing image, we use two retrieval modules to retrieve representations of training images with the same attribute and object, respectively. The primitive representations of the input image are augmented by using the retrieved representations, for composition recognition. By referencing semantically similar images, the proposed method is capable of recalling knowledge of seen primitives for compositional generalization. Experiments on three widely-used datasets show the effectiveness of the proposed method.
7
Cui, Ruixiang, Rahul Aralikatte, Heather Lent i Daniel Hershcovich. "Compositional Generalization in Multilingual Semantic Parsing over Wikidata". Transactions of the Association for Computational Linguistics 10 (2022): 937–55. http://dx.doi.org/10.1162/tacl_a_00499.
Pełny tekst źródłaStreszczenie:
Abstract Semantic parsing (SP) allows humans to leverage vast knowledge resources through natural interaction. However, parsers are mostly designed for and evaluated on English resources, such as CFQ (Keysers et al., 2020), the current standard benchmark based on English data generated from grammar rules and oriented towards Freebase, an outdated knowledge base. We propose a method for creating a multilingual, parallel dataset of question-query pairs, grounded in Wikidata. We introduce such a dataset, which we call Multilingual Compositional Wikidata Questions (MCWQ), and use it to analyze the compositional generalization of semantic parsers in Hebrew, Kannada, Chinese, and English. While within- language generalization is comparable across languages, experiments on zero-shot cross- lingual transfer demonstrate that cross-lingual compositional generalization fails, even with state-of-the-art pretrained multilingual encoders. Furthermore, our methodology, dataset, and results will facilitate future research on SP in more realistic and diverse settings than has been possible with existing resources.
8
Guo, Yinuo, Hualei Zhu, Zeqi Lin, Bei Chen, Jian-Guang Lou i Dongmei Zhang. "Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization". Proceedings of the AAAI Conference on Artificial Intelligence 35, nr 9 (18.05.2021): 7601–9. http://dx.doi.org/10.1609/aaai.v35i9.16930.
Pełny tekst źródłaStreszczenie:
Human intelligence exhibits compositional generalization (i.e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability. In this paper, we revisit iterative back-translation, a simple yet effective semi-supervised method, to investigate whether and how it can improve compositional generalization. In this work: (1) We first empirically show that iterative back-translation substantially improves the performance on compositional generalization benchmarks (CFQ and SCAN). (2) To understand why iterative back-translation is useful, we carefully examine the performance gains and find that iterative back-translation can increasingly correct errors in pseudo-parallel data. (3) To further encourage this mechanism, we propose curriculum iterative back-translation, which better improves the quality of pseudo-parallel data, thus further improving the performance.
9
Logeswaran, Lajanugen, Wilka Carvalho i Honglak Lee. "Learning Compositional Tasks from Language Instructions". Proceedings of the AAAI Conference on Artificial Intelligence 37, nr 11 (26.06.2023): 13300–13308. http://dx.doi.org/10.1609/aaai.v37i11.26561.
Pełny tekst źródłaStreszczenie:
The ability to combine learned knowledge and skills to solve novel tasks is a key aspect of generalization in humans that allows us to understand and perform tasks described by novel language utterances. While progress has been made in supervised learning settings, no work has yet studied compositional generalization of a reinforcement learning agent following natural language instructions in an embodied environment. We develop a set of tasks in a photo-realistic simulated kitchen environment that allow us to study the degree to which a behavioral policy captures the systematicity in language by studying its zero-shot generalization performance on held out natural language instructions. We show that our agent which leverages a novel additive action-value decomposition in tandem with attention based subgoal prediction is able to exploit composition in text instructions to generalize to unseen tasks.
10
Petit, Alban, i Caio Corro. "On Graph-based Reentrancy-free Semantic Parsing". Transactions of the Association for Computational Linguistics 11 (2023): 703–22. http://dx.doi.org/10.1162/tacl_a_00570.
Pełny tekst źródłaStreszczenie:
Abstract We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on GeoQuery, Scan, and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.
11
Liu, Anthony, Sungryull Sohn, Mahdi Qazwini i Honglak Lee. "Learning Parameterized Task Structure for Generalization to Unseen Entities". Proceedings of the AAAI Conference on Artificial Intelligence 36, nr 7 (28.06.2022): 7534–41. http://dx.doi.org/10.1609/aaai.v36i7.20718.
Pełny tekst źródłaStreszczenie:
Real world tasks are hierarchical and compositional. Tasks can be composed of multiple subtasks (or sub-goals) that are dependent on each other. These subtasks are defined in terms of entities (e.g., "apple", "pear") that can be recombined to form new subtasks (e.g., "pickup apple", and "pickup pear"). To solve these tasks efficiently, an agent must infer subtask dependencies (e.g. an agent must execute "pickup apple" before "place apple in pot"), and generalize the inferred dependencies to new subtasks (e.g. "place apple in pot" is similar to "place apple in pan"). Moreover, an agent may also need to solve unseen tasks, which can involve unseen entities. To this end, we formulate parameterized subtask graph inference (PSGI), a method for modeling subtask dependencies using first-order logic with factored entities. To facilitate this, we learn parameter attributes in a zero-shot manner, which are used as quantifiers (e.g. is_pickable(X)) for the factored subtask graph. We show this approach accurately learns the latent structure on hierarchical and compositional tasks more efficiently than prior work, and show PSGI can generalize by modelling structure on subtasks unseen during adaptation.
12
Bogin, Ben, Sanjay Subramanian, Matt Gardner i Jonathan Berant. "Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering". Transactions of the Association for Computational Linguistics 9 (2021): 195–210. http://dx.doi.org/10.1162/tacl_a_00361.
Pełny tekst źródłaStreszczenie:
Abstract Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model induces latent trees, driven by end-to-end (the answer) supervision only. We show that this inductive bias towards tree structures dramatically improves systematic generalization to out-of- distribution examples, compared to strong baselines on an arithmetic expressions benchmark as well as on C losure, a dataset that focuses on systematic generalization for grounded question answering. On this challenging dataset, our model reaches an accuracy of 96.1%, significantly higher than prior models that almost perfectly solve the task on a random, in-distribution split.
13
Wu, Zhengxuan, Christopher D. Manning i Christopher Potts. "ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation". Transactions of the Association for Computational Linguistics 11 (2023): 1719–33. http://dx.doi.org/10.1162/tacl_a_00623.
Pełny tekst źródłaStreszczenie:
Abstract Compositional generalization benchmarks for semantic parsing seek to assess whether models can accurately compute meanings for novel sentences, but operationalize this in terms of logical form (LF) prediction. This raises the concern that semantically irrelevant details of the chosen LFs could shape model performance. We argue that this concern is realized for the COGS benchmark (Kim and Linzen, 2020). COGS poses generalization splits that appear impossible for present-day models, which could be taken as an indictment of those models. However, we show that the negative results trace to incidental features of COGS LFs. Converting these LFs to semantically equivalent ones and factoring out capabilities unrelated to semantic interpretation, we find that even baseline models get traction. A recent variable-free translation of COGS LFs suggests similar conclusions, but we observe this format is not semantically equivalent; it is incapable of accurately representing some COGS meanings. These findings inform our proposal for ReCOGS, a modified version of COGS that comes closer to assessing the target semantic capabilities while remaining very challenging. Overall, our results reaffirm the importance of compositional generalization and careful benchmark task design.
14
Buch, Shyamal, Li Fei-Fei i Noah D. Goodman. "Neural Event Semantics for Grounded Language Understanding". Transactions of the Association for Computational Linguistics 9 (2021): 875–90. http://dx.doi.org/10.1162/tacl_a_00402.
Pełny tekst źródłaStreszczenie:
Abstract We present a new conjunctivist framework, neural event semantics (NES), for compositional grounded language understanding. Our approach treats all words as classifiers that compose to form a sentence meaning by multiplying output scores. These classifiers apply to spatial regions (events) and NES derives its semantic structure from language by routing events to different classifier argument inputs via soft attention. NES is trainable end-to-end by gradient descent with minimal supervision. We evaluate our method on compositional grounded language tasks in controlled synthetic and real-world settings. NES offers stronger generalization capability than standard function-based compositional frameworks, while improving accuracy over state-of-the-art neural methods on real-world language tasks.
15
CHATZIKOKOLAKIS, KONSTANTINOS, CATUSCIA PALAMIDESSI i CHRISTELLE BRAUN. "Compositional methods for information-hiding". Mathematical Structures in Computer Science 26, nr 6 (24.11.2014): 908–32. http://dx.doi.org/10.1017/s0960129514000292.
Pełny tekst źródłaStreszczenie:
Systems concerned with information hiding often use randomization to obfuscate the link between the observables and the information to be protected. The degree of protection provided by a system can be expressed in terms of the probability of error associated with the inference of the secret information. We consider a probabilistic process calculus to specify such systems, and we study how the operators affect the probability of error. In particular, we characterize constructs that have the property of not decreasing the degree of protection, and that can therefore be considered safe in the modular construction of these systems. As a case study, we apply these techniques to the dining cryptographers, and we derive a generalization of Chaum's strong anonymity result.
16
Basu, Sourya, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Vijil Chenthamarakshan, Kush R. Varshney, Lav R. Varshney i Payel Das. "Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models". Proceedings of the AAAI Conference on Artificial Intelligence 37, nr 6 (26.06.2023): 6788–96. http://dx.doi.org/10.1609/aaai.v37i6.25832.
Pełny tekst źródłaStreszczenie:
We introduce equi-tuning, a novel fine-tuning method that transforms (potentially non-equivariant) pretrained models into group equivariant models while incurring minimum L_2 loss between the feature representations of the pretrained and the equivariant models. Large pretrained models can be equi-tuned for different groups to satisfy the needs of various downstream tasks. Equi-tuned models benefit from both group equivariance as an inductive bias and semantic priors from pretrained models. We provide applications of equi-tuning on three different tasks: image classification, compositional generalization in language, and fairness in natural language generation (NLG). We also provide a novel group-theoretic definition for fairness in NLG. The effectiveness of this definition is shown by testing it against a standard empirical method of fairness in NLG. We provide experimental results for equi-tuning using a variety of pretrained models: Alexnet, Resnet, VGG, and Densenet for image classification; RNNs, GRUs, and LSTMs for compositional generalization; and GPT2 for fairness in NLG. We test these models on benchmark datasets across all considered tasks to show the generality and effectiveness of the proposed method.
17
Gould, Isaac. "Multiple movement dependencies and parasitic gaps". Canadian Journal of Linguistics/Revue canadienne de linguistique 65, nr 1 (14.01.2020): 110–21. http://dx.doi.org/10.1017/cnj.2019.33.
Pełny tekst źródłaStreszczenie:
Nissenbaum (2000) and Heck and Himmelreich (2017) (henceforth HH) are two prominent works that are noteworthy for focusing on the interaction of multiple movement dependencies (MMDs) and parasitic gaps (PGs). However, these two works consider disjoint and contrasting types of data paradigms. In this squib, I take both types of paradigms into consideration. In doing so, there are three inter-related questions that arise for our understanding of PGs (and in particular for PGs that involve certain MMDs). The first question asks what the correct descriptive generalizations about PG paradigms are. Going beyond such a generalization, we can also ask how to properly account for the data (and whether a unified analysis is possible). Finally, and more specifically, we can ask how to account for the compositional semantics of PGs, especially those involving MMDs.
18
Okazaki, Akira, i Shuichi Kawano. "Multi-Task Learning for Compositional Data via Sparse Network Lasso". Entropy 24, nr 12 (17.12.2022): 1839. http://dx.doi.org/10.3390/e24121839.
Pełny tekst źródłaStreszczenie:
Multi-task learning is a statistical methodology that aims to improve the generalization performances of estimation and prediction tasks by sharing common information among multiple tasks. On the other hand, compositional data consist of proportions as components summing to one. Because components of compositional data depend on each other, existing methods for multi-task learning cannot be directly applied to them. In the framework of multi-task learning, a network lasso regularization enables us to consider each sample as a single task and construct different models for each one. In this paper, we propose a multi-task learning method for compositional data using a sparse network lasso. We focus on a symmetric form of the log-contrast model, which is a regression model with compositional covariates. Our proposed method enables us to extract latent clusters and relevant variables for compositional data by considering relationships among samples. The effectiveness of the proposed method is evaluated through simulation studies and application to gut microbiome data. Both results show that the prediction accuracy of our proposed method is better than existing methods when information about relationships among samples is appropriately obtained.
19
Korbak, Tomasz, Julian Zubek, Łukasz Kuciński, Piotr Miłoś i Joanna Rączaszek-Leonardi. "Interaction history as a source of compositionality in emergent communication". Interaction Studies 22, nr 2 (31.12.2021): 212–43. http://dx.doi.org/10.1075/is.21020.kor.
Pełny tekst źródłaStreszczenie:
Abstract In this paper, we explore interaction history as a particular source of pressure for achieving emergent compositional communication in multi-agent systems. We propose a training regime implementing template transfer, the idea of carrying over learned biases across contexts. In the presented method, a sender-receiver dyad is first trained with a disentangled pair of objectives, and then the receiver is transferred to train a new sender with a standard objective. Unlike other methods (e.g. the obverter algorithm), the template transfer approach does not require imposing inductive biases on the architecture of the agents. We experimentally show the emergence of compositional communication using topographical similarity, zero-shot generalization and context-independence as evaluation metrics. The presented approach is connected to an important line of work in semiotics and developmental psycholinguistics: it supports a conjecture that compositional communication is scaffolded on simpler communication protocols.
20
Moro, Andrea. "The geometry of predication: a configurational derivation of the defining property of clause structure". Philosophical Transactions of the Royal Society B: Biological Sciences 375, nr 1791 (16.12.2019): 20190310. http://dx.doi.org/10.1098/rstb.2019.0310.
Pełny tekst źródłaStreszczenie:
Predication is the fundamental grammatical relation defining clausal structures in all (and only) human languages. This notion is by definition compositional, since it consists of a link between a subject and a predicate. The central question addressed here is whether this traditional notion, which has never been dismissed ever since the canonical models of Ancient Greek linguistics, can be derived at a formal level from more abstract compositional algorithms. Capitalizing on predication in copular sentences, which allow factoring out non-essential aspects of this phenomenon, such as the morphological asymmetry between verbs and nouns, I propose a configurational approach to predication. This new approach is based on the notion of symmetry as derived by purely compositional mechanisms. Finally, I address some theoretical and empirical consequences of this generalization including those pertaining to neurolinguistics. This article is part of the theme issue ‘Towards mechanistic models of meaning composition’.
21
Weir, David, Julie Weeds, Jeremy Reffin i Thomas Kober. "Aligning Packed Dependency Trees: A Theory of Composition for Distributional Semantics". Computational Linguistics 42, nr 4 (grudzień 2016): 727–61. http://dx.doi.org/10.1162/coli_a_00265.
Pełny tekst źródłaStreszczenie:
We present a new framework for compositional distributional semantics in which the distributional contexts of lexemes are expressed in terms of anchored packed dependency trees. We show that these structures have the potential to capture the full sentential contexts of a lexeme and provide a uniform basis for the composition of distributional knowledge in a way that captures both mutual disambiguation and generalization.
22
Iranshahr, Alireza, Denis V. Voskov i Hamdi A. Tchelepi. "Tie-simplex based compositional space parameterization: Continuity and generalization to multiphase systems". AIChE Journal 59, nr 5 (25.09.2012): 1684–701. http://dx.doi.org/10.1002/aic.13919.
Pełny tekst źródła
23
Gill, John. "Inner composition of analytic mappings on the unit disk". International Journal of Mathematics and Mathematical Sciences 14, nr 2 (1991): 221–26. http://dx.doi.org/10.1155/s0161171291000236.
Pełny tekst źródłaStreszczenie:
A basic theorem of iteration theory (Henrici [6]) states thatfanalytic on the interior of the closed unit diskDand continuous onDwithInt(D)f(D)carries any pointz ϵ Dto the unique fixed pointα ϵ Doff. That is to say,fn(z)→αasn→∞. In [3] and [5] the author generalized this result in the following way: LetFn(z):=f1∘…∘fn(z). Thenfn→funiformly onDimpliesFn(z)λ, a constant, for allz ϵ D. This kind of compositional structure is a generalization of a limit periodic continued fraction. This paper focuses on the convergence behavior of more general inner compositional structuresf1∘…∘fn(z)where thefj's are analytic onInt(D)and continuous onDwithInt(D)fj(D), but essentially random. Applications include analytic functions defined by this process.
24
Lyu, Qiang, i Weiqiang Wang. "Compositional Prototypical Networks for Few-Shot Classification". Proceedings of the AAAI Conference on Artificial Intelligence 37, nr 7 (26.06.2023): 9011–19. http://dx.doi.org/10.1609/aaai.v37i7.26082.
Pełny tekst źródłaStreszczenie:
It is assumed that pre-training provides the feature extractor with strong class transferability and that high novel class generalization can be achieved by simply reusing the transferable feature extractor. In this work, our motivation is to explicitly learn some fine-grained and transferable meta-knowledge so that feature reusability can be further improved. Concretely, inspired by the fact that humans can use learned concepts or components to help them recognize novel classes, we propose Compositional Prototypical Networks (CPN) to learn a transferable prototype for each human-annotated attribute, which we call a component prototype. We empirically demonstrate that the learned component prototypes have good class transferability and can be reused to construct compositional prototypes for novel classes. Then a learnable weight generator is utilized to adaptively fuse the compositional and visual prototypes. Extensive experiments demonstrate that our method can achieve state-of-the-art results on different datasets and settings. The performance gains are especially remarkable in the 5-way 1-shot setting. The code is available at https://github.com/fikry102/CPN.
25
Герасименко, О. Д., К. Л. Пашкевич, Г. В. Омельченко, Б. П. Загрійчук i О. М. Колосниченко. "ХУДОЖНЬО-КОМПОЗИЦІЙНІ ОСОБЛИВОСТІ ДИТЯЧОГО КОСТЮМУ У КОЛЕКЦІЯХ ВИСОКОЇ МОДИ ХХ – ПОЧАТКУ ХХІ СТ." Art and Design, nr 4 (3.02.2020): 21–33. http://dx.doi.org/10.30857/2617-0272.2019.4.2.
Pełny tekst źródłaStreszczenie:
The purpose of the work is to study the artistic and compositional features in children's collections of haute couture houses and determine the patterns of their repetition in the design of children's costumes in the 20th and early 21st century. To achieve this goal, a historical study of materials, a visual-analytical method, morphological and compositional-structural analysis were applied. The evolution of children's costume in the high fashion collections in the and early 21st century is investigated and the main trends in children's fashion for a given period of time are analyzed. The artistic and compositional features of the children's costume are identified, the most characteristic artistic and structural elements of children's clothing are identified: three-dimensional shape, color scheme and fabric pattern, structural and decorative elements and decoration. The regularity of repeating the pattern of fabric in the collections of children's clothing of the Fashion houses in the 20th and early 21st century is established. The collected materials and their analysis made it possible to establish regularity of repeating of artistic and compositional features in a children's costume, such as a fabric pattern and decoration in different years in models of children's clothing of High Fashion Houses. Practical significance lies in the generalization of artistic compositional features and the identification of leading trends in the artistic compositional solution of children's costumes in the high fashion collections in the 20th and early 21st century. The results will make it possible to predict trends in children's fashion, design actual models of clothing for children and can be used in further research on the design of children's clothing.
26
Yao, Huaxiu. "Towards Reliable Learning in the Wild: Generalization and Adaptation". Proceedings of the AAAI Conference on Artificial Intelligence 38, nr 20 (24.03.2024): 22683. http://dx.doi.org/10.1609/aaai.v38i20.30299.
Pełny tekst źródłaStreszczenie:
The real-world deployment of machine learning algorithms often poses challenges due to shifts in data distributions and tasks. These shifts can lead to a degradation in model performance, as the model may not have encountered such changes during training. Additionally, they can make it difficult for the model to generalize to new scenarios and can result in poor performance in real-world applications. In this talk, I will present our research on building machine learning models that are highly generalizable and easily adaptable to different shifts. Specifically, I will first discuss our approach to improving out-of-distribution robustness and mitigating spurious correlations by training environment-invariant models through selective augmentation and post-hoc rectification. Second, I will present our techniques for continuous and rapid adaptation of models to new tasks and environments. This includes methods to facilitate compositional generalization and adaptation by extracting relationships from historical observations and to enhance reliable adaptation even in the face of imperfect observations. Additionally, I will showcase our successful practices for addressing shifts in real-world applications, such as in the healthcare, e-commerce, and transportation industries. The talk will also touch upon the remaining challenges and outline future research directions in this area.
27
Tsarkov, Dmitry, Tibor Tihon, Nathan Scales, Nikola Momchev, Danila Sinopalnikov i Nathanael Schärli. "*-CFQ: Analyzing the Scalability of Machine Learning on a Compositional Task". Proceedings of the AAAI Conference on Artificial Intelligence 35, nr 11 (18.05.2021): 9949–57. http://dx.doi.org/10.1609/aaai.v35i11.17195.
Pełny tekst źródłaStreszczenie:
We present *-CFQ ("star-CFQ"): a suite of large-scale datasets of varying scope based on the CFQ semantic parsing benchmark, designed for principled investigation of the scalability of machine learning systems in a realistic compositional task setting. Using this suite, we conduct a series of experiments investigating the ability of Transformers to benefit from increased training data size under conditions of fixed computational cost. We show that compositional generalization remains a challenge at all training sizes, and we show that increasing the scope of natural language leads to consistently higher error rates, which are only partially offset by increased training data. We further show that while additional training data from a related domain improves the accuracy in data-starved situations, this improvement is limited and diminishes as the distance from the related domain to the target domain increases.
28
PRESSON, NORA, NURIA SAGARRA, BRIAN MACWHINNEY i JOHN KOWALSKI. "Compositional production in Spanish second language conjugation". Bilingualism: Language and Cognition 16, nr 4 (20.12.2012): 808–28. http://dx.doi.org/10.1017/s136672891200065x.
Pełny tekst źródłaStreszczenie:
Dual-route models of second language (L2) morphology (Clahsen & Felser, 2006; Ullman, 2004) argue that adult L2 learners rely on full-form retrieval, and therefore cannot use combination to produce inflected forms. We tested this prediction with learning of Spanish verb conjugations. Beginning (Experiment 1) and intermediate (Experiment 2) learners (total N = 816) completed 80–90 minutes of web-based training, conjugating regular and subregular verbs in present and preterite tense. Tests of generalization items showed that training led to substantial improvement, equally for metalinguistic and analogical feedback. Comparison with an untrained group showed that gains were maintained 18 weeks after training. In contrast with dual-route model predictions, pre-test accuracy and learning gains were strongly predicted by conjugation pattern, showing that full-form retrieval was insufficient to explain learner performance. Results indicate that adult L2 learners apply compositional analysis, and that conjugation patterns are learned on the basis of their relative cue validity.
29
Alves de Oliveira, Helder, Liduino Pitombeira i Raphael Sousa Santos. "Gestalt Modeling of Ponteio No. 28 by Camargo Guarnieri". Indiana Theory Review 39, nr 1 (marzec 2024): 110–45. http://dx.doi.org/10.2979/itr.00005.
Pełny tekst źródłaStreszczenie:
Abstract: In this work, the analytical-compositional methodology called Gestalt Modeling (hereinafter GM) is used to analyze Camargo Guarnieri’s Ponteio No. 28 , from the perspective of three laws of perceptual organization according to Gestalt Psychology. The objective of the analysis is to provide some definitions of the hypothetical system that generated this musical work by Guarnieri and to plan a musical composition for solo piano entitled Aboio . This planning will be described in detail in this paper. GM comes from the convergence between two fields of knowledge, Gestalt Theory and Systemic Modeling, whose definitions will be introduced in this work. From the structural dispositions of an intertext (a pre-existing musical work), according to certain Gestalt laws of perceptual organization, it is possible to create new works based on these structures. GM basically consists of two phases: 1) analysis from the perspective of Gestalt Theory; and 2) relational generalization, which consists of considering only the relationships between objects detected in the analytical phase, disregarding their particular values. The result of this methodology is a hypothetical compositional system that generates the work used in the planning of the new work Aboio . There are aesthetic similarities at a deep level between this work and the intertext, and there are significant differences related to aspects not included in the compositional system and to the filling of relational structures contained in the system. As final results, GM presents itself as: 1) a useful and differentiated resource for the analysis of musical works and also for compositional purposes, for coherently presenting new ways of organizing musical elements; and 2) possible methodology for compositional pedagogy as it provides subsidies for a conscious practice and the development of the student’s own compositional language.
30
Grosevych, I. V. "GOTHIC FICTION: FIGURATIVE PLOT PARADIGM". PRECARPATHIAN BULLETIN OF THE SHEVCHENKO SCIENTIFIC SOCIETY Word, nr 2(54) (22.01.2019): 275–87. http://dx.doi.org/10.31471/2304-7402-2019-2(54)-275-287.
Pełny tekst źródłaStreszczenie:
The article deals with the theoretical generalization of the attributes of a poetic of gothic, in particular in the article is analyzed in details the figurative-motive and plot-compositional levels; is traced the evolution of the image of Devil; is identified the triune category − mystery / horror / suspense – as a genre constant of gothic fiction; is identified the road archetype; is analyzed the functionality of gothic, contrast as the dominant feature of the gothic paradigm; and also is grounded the philosophical doctrine of the theodicy as one of the fundamental basis of all gothic fiction.
31
Li, Shilan, Jianxin Shi, Paul Albert i Hong-Bin Fang. "Dependence Structure Analysis and Its Application in Human Microbiome". Mathematics 11, nr 1 (20.12.2022): 9. http://dx.doi.org/10.3390/math11010009.
Pełny tekst źródłaStreszczenie:
The human microbiome has been recently shown to be associated with disease risks and has important implications in risk stratification and precision medicine. Due to abundant taxa in the human body, microbiome data are high-dimensional and compositional. Dirichlet distributions and their generalization are used to characterize the dependence structures of microbial data. Another existing method for fitting microbiome data employed Gaussian graphical model using the centered log-transformation (CLR). However, Dirichlet distributions are not able to infer networks or to estimate some extremely rare probabilities. On the other hand, it is hard to interpret the network analysis results using CLR. Furthermore, the data analysis showed that there is a lack of efficient multivariate distributions for fitting microbiome data, which results in inadequate statistical inferences. In this paper, we propose new multivariate distributions for modeling the dependence structures of the high dimensional and compositional microbiome data using inverse gamma distributions and copula techniques. The data analysis in the American gut project shows our proposed methods perform well.
32
Safronova, A. V. "MODERN UKRAINIAN PHOTO BOOK AS AN OBJECT OF CONCEPTUAL ART OF POSTMODERNISM". Art and Design, nr 2 (11.08.2021): 52–62. http://dx.doi.org/10.30857/2617-0272.2021.2.5.
Pełny tekst źródłaStreszczenie:
Purpose. The purpose of the study is to identify the features of modern Ukrainian photo books, which have become a striking example of following the trends of postmodern art. Methodology. The study is based on the integrated use of historical, comparative methods, systems analysis, synthesis, generalization. Results. The modern Ukrainian photo book is considered as a work of conceptual art of postmodernism. Certain artistic and compositional features and design techniques of Ukranian photobooks are identified; originality of form; author's presentation of textual, content and visual components of the indoor unit: inclusion of ready-made images (ready-made) and photo manipulation, use of collages, photos of utilitarian objects, etc. Scientific novelty. On the example of art history analysis of a number of well-known Ukrainian photobooks, the characteristic features of the photobook as an object of modern conceptual art is determined, the features of figurative, stylistic, artistic and compositional design solutions are systematized. Practical significance. The artistic and compositional features and design techniques used by photographers in the implementation of creative ideas have been identified, the theoretical basis of modern conceptual art have been expanded that can be useful in future creative projects of photobooks that will have both artistic and commercial value.
33
Pylypchuk, Oksana, Oleksandr Kashchenko i Andrіi Polubok. "The Role of an Art Object in the Formation of Characteristic Features of Interior Space". Demiurge: Ideas, Technologies, Perspectives of Design 7, nr 1 (1.04.2024): 138–50. http://dx.doi.org/10.31866/2617-7951.7.1.2024.300933.
Pełny tekst źródłaStreszczenie:
The aim of the article is to study the role of different types of art objects in the formation of characteristic features of interior space. Research methods included bibliographic, typological and comparative analysis, field survey, compositional method, systematization and generalization. The scientific novelty lies in the research, analysis and systematization of the functional and aesthetic role of art objects in the formation of characteristic features of interior space. Conclusions. As a result of the study, the main features of the interior space, which can be achieved by placing an art object in it, were determined: intensification, assimilation, hyperbolization and transformation. Thus, the intensification of the interior is achieved through the dominant position of the art object, its compositional coherence with other elements, the subordination of rhythmic structures to it, and the creation of space for the effects of dynamism and expressiveness. Assimilation is achieved by subtly combining the geometric shapes of the interior space and the art object, creating a sense of balance, homogeneity, and compositional completeness. Hyperbolization relies on a pronounced semantic and stylistic contrast between the art object and the interior elements, resulting in the effect of compositional dissonance, revitalization, and at times, irony, sarcasm, and satire. Transformation involves visually altering the geometric form, size, or shape of both the interior space and the art object. This is achieved through methods such as dismemberment, emphasis, and the reconfiguration of spatial elements, leading to the effect of compositional asymmetry, dissymmetry, and dynamism. The study tested specific results in the design work of design students. The prospect for further research is to analyze the role of art objects in the qualitative transformation of modern interiors, to identify and systematize modern trends in the relationship between fine art and the object and spatial environment.
34
Наталія Дігтяр i Олександр Тарасенко. "COMPOSITION IN THE LANDSCAPE: ART AND PEDAGOGICAL ASPECT". Problems of Modern Teacher Training, nr 2(22) (1.10.2021): 49–55. http://dx.doi.org/10.31499/2307-4914.2(22).2020.219394.
Pełny tekst źródłaStreszczenie:
The author emphasizes the importance of studying the landscape as a genre of fine arts by students. The laws and techniques of composition are the basis, the basis of writing works of all genres of painting that is why compositional competencies are the main place in the structure of art education. This is especially true of landscape composition.Creating a landscape involves drawing in the open air, outdoors. The work should start with finding the best location – landscaping locations. It is well known in an art practice that any composition begins with sketches. The same goes for landscape composition. It is emphasized that in the course of future teachers' of fine arts professional training should be acquainted with the basic laws of the construction of landscape composition on the plane, the means of applying the method of golden intersection in landscapes, methods of reaching the depth of space in the image of the surrounding nature in different compositional formats and compositional generalization; step-by-step work from compositional searches to detailing and completion of a complete artistic landscape image. Art educators argue that all the details in the landscape should be well connected and helped to express the overall idea of the composition. To do this, students need to focus on more area characteristic features, select the most typical landscape objects. It is revealed that the landscape is not just a copy of nature from nature, but also the expression of the artist's attitude to nature, the transfer of the artist's own mood, their experiences and emotions. The author emphasizes the importance of studying the соmpositional techniques in the landscape should be applied not formally, but in order to best express the main idea of the artist. The author agrees with the opinion of artist-educators, who argue that students should be given the opportunity to independently set certain compositional tasks and perform them independently in the creation of a landscape.
35
Kolisnyk, O. V., L. V. Ocheretna, M. I. Yakovlev, O. V. Kolosnichenko, K. L. Pashkevich i O. M. Kretova. "TENDENCIES AND ART TECHNIQUES IN CONTEMPORARY COMIC BOOK GRAPHIC DESIGN". Art and Design, nr 3 (13.11.2020): 34–45. http://dx.doi.org/10.30857/2617-0272.2020.3.2.
Pełny tekst źródłaStreszczenie:
Purpose. Exploring of the distinctive features of modern comics, their artistic and compositional solutions, types, main trends in American, European and Asian culture. Definition of the original formation of modern Ukrainian comics. Methodology. The basis of the research methodology includes integrated use of historical and comparative methods, system analysis, synthesis, generalization. Results. Basing on the analysis of modern comic book content, the history of comics and its perception by the audience as a modern media text are revealed, characteristics of individual elements in comics are systematized. The specifics of the artistic and compositional system of modern comics, the nature of figurative and stylistic techniques, graphic features of American, European, Asian, Ukrainian comics are determined. Patterns which are inherent in comics as visual narratives of different socio-cultural parts of the world, as well as aspects that shape modern Ukrainian comics, are considered. Scientific novelty. Characteristics of comics as an object of graphic design are determined: features of artistic and compositional design solutions in different regions of the world are systematized; leading trends in the development of specific types of comics in the United States, Europe, Asia and Ukraine are revealed. Practical significance. Based on art analysis of comic book types and by identifying trends in their development within modern art the specifics of the further development of comics are determined and ideas for future creative projects are presented, features that have both artistic and commercial value are indicated.
36
Mel’nyk, Oksa, i Julija Shtets. "Artistic and compositional features of G. Narbut’s book graphics and possibilities of their interpretation in modern graphic design". Almanac "Culture and Contemporaneity", nr 1 (31.08.2021): 104–8. http://dx.doi.org/10.32461/2226-0285.1.2021.238595.
Pełny tekst źródłaStreszczenie:
The purpose of the article is to generalize and systematize the graphic and compositional parameters of G. Narbut's book graphics and to find ways of their interpretation in modern graphic design. The methodology of the research is represented by general scientific and special methods. Analysis, synthesis, comparative, systemic, and empirical methods have become basic in the study of literature and empirical material. Comparative, compositional, visual-graphic, and descriptive methods were used to identify the figurative and semantic characteristics of G. Narbut's graphic works and their influence on modern design. The scientific novelty of the work lies in the complex analysis of G. Narbut's graphic works, revealing the peculiarities of their graphic-compositional solutions and determining the principles of their interpretation in modern design practice. Conclusions. It is revealed that in the context of the formation of the national model of Ukrainian graphic design today, the work of G. Narbut needs not copying, but careful rethinking. The study, systematization, and generalization of the artist's experience open the prospect of development and interpretation in the works of designers of the XXI century. The algorithm of such interpretation is a holistic approach to design and composition; rethinking form from the point of view of traditional art; synthesis of geometric calculation and complex artistic image; the contrast between primary and secondary elements; rhythmic repetitions; emphasis on the vertical axis of symmetry and the author's presentation, corresponding to the demands of today.
37
Колосніченко, О. В., К. Л. Пашкевич i Ю. Я. Лозко. "ХУДОЖНЬО-ОБРАЗНІ ОСОБЛИВОСТІ СПЕЦОДЯГУ В ДИЗАЙНІ ХХ СТОЛІТТЯ". Art and Design, nr 1 (13.05.2019): 87–104. http://dx.doi.org/10.30857/2617-0272.2019.1.8.
Pełny tekst źródłaStreszczenie:
Analysis and generalization of scientific and practical developments in the aesthetic-harmonic design of special-purpose clothing: features of forming and means of compositional expressiveness. For the analysis of literary sources of information, the literary-analytical method was used; for the analysis of visual sources - the visual-analytical method. The method of deduction (conclusions about the process of forming uniforms for workers of coal and mining mines) and incomplete induction (manifestations of compositional expression) were used. The practical developments and conceptual provisions of the activity of constructivist artists in the creation of clothes for labor are considered. The situation in the field of designing overalls in the territory of the Ukrainian SSR and the USSR as a whole has been investigated. The characteristic of changes in the form of overalls, intended for workers of coal mining and mining mines during 1920-1980 years was received. The overalls are considered as an art object and analyzed the manifestations of possible means of compositional expressiveness, the principles of combining forms in suits of various special purpose. The means of compositional expressiveness and the volume-spatial form of special purpose clothes from the position of visual perception are systematized. The modification of the form of overalls made during the 1920-1980 years for workers of coal mining and mining mines during the period was investigated. The obtained results of the research give an opportunity to form an idea of the aesthetic component in the general concept of special purpose clothes and to supplement the available theoretical information in this field. Also, the findings of the study may serve as an additional informative source at the stage of artistic-constructive analysis in modern design engineering not only the class of industrial clothing, but also domestic.
38
Niu, Guanglin, Yongfei Zhang, Bo Li, Peng Cui, Si Liu, Jingyang Li i Xiaowei Zhang. "Rule-Guided Compositional Representation Learning on Knowledge Graphs". Proceedings of the AAAI Conference on Artificial Intelligence 34, nr 03 (3.04.2020): 2950–58. http://dx.doi.org/10.1609/aaai.v34i03.5687.
Pełny tekst źródłaStreszczenie:
Representation learning on a knowledge graph (KG) is to embed entities and relations of a KG into low-dimensional continuous vector spaces. Early KG embedding methods only pay attention to structured information encoded in triples, which would cause limited performance due to the structure sparseness of KGs. Some recent attempts consider paths information to expand the structure of KGs but lack explainability in the process of obtaining the path representations. In this paper, we propose a novel Rule and Path-based Joint Embedding (RPJE) scheme, which takes full advantage of the explainability and accuracy of logic rules, the generalization of KG embedding as well as the supplementary semantic structure of paths. Specifically, logic rules of different lengths (the number of relations in rule body) in the form of Horn clauses are first mined from the KG and elaborately encoded for representation learning. Then, the rules of length 2 are applied to compose paths accurately while the rules of length 1 are explicitly employed to create semantic associations among relations and constrain relation embeddings. Moreover, the confidence level of each rule is also considered in optimization to guarantee the availability of applying the rule to representation learning. Extensive experimental results illustrate that RPJE outperforms other state-of-the-art baselines on KG completion task, which also demonstrate the superiority of utilizing logic rules as well as paths for improving the accuracy and explainability of representation learning.
39
Aghel, Babak, Salah I. Yahya, Abbas Rezaei i Falah Alobaid. "A Dynamic Recurrent Neural Network for Predicting Higher Heating Value of Biomass". International Journal of Molecular Sciences 24, nr 6 (17.03.2023): 5780. http://dx.doi.org/10.3390/ijms24065780.
Pełny tekst źródłaStreszczenie:
The higher heating value (HHV) is the main property showing the energy amount of biomass samples. Several linear correlations based on either the proximate or the ultimate analysis have already been proposed for predicting biomass HHV. Since the HHV relationship with the proximate and ultimate analyses is not linear, nonlinear models might be a better alternative. Accordingly, this study employed the Elman recurrent neural network (ENN) to anticipate the HHV of different biomass samples from both the ultimate and proximate compositional analyses as the model inputs. The number of hidden neurons and the training algorithm were determined in such a way that the ENN model showed the highest prediction and generalization accuracy. The single hidden layer ENN with only four nodes, trained by the Levenberg–Marquardt algorithm, was identified as the most accurate model. The proposed ENN exhibited reliable prediction and generalization performance for estimating 532 experimental HHVs with a low mean absolute error of 0.67 and a mean square error of 0.96. In addition, the proposed ENN model provides a ground to clearly understand the dependency of the HHV on the fixed carbon, volatile matter, ash, carbon, hydrogen, nitrogen, oxygen, and sulfur content of biomass feedstocks.
40
Chen, Qiaochu, Arko Banerjee, Çağatay Demiralp, Greg Durrett i Işıl Dillig. "Data Extraction via Semantic Regular Expression Synthesis". Proceedings of the ACM on Programming Languages 7, OOPSLA2 (16.10.2023): 1848–77. http://dx.doi.org/10.1145/3622863.
Pełny tekst źródłaStreszczenie:
Many data extraction tasks of practical relevance require not only syntactic pattern matching but also semantic reasoning about the content of the underlying text. While regular expressions are very well suited for tasks that require only syntactic pattern matching, they fall short for data extraction tasks that involve both a syntactic and semantic component. To address this issue, we introduce semantic regexes, a generalization of regular expressions that facilitates combined syntactic and semantic reasoning about textual data. We also propose a novel learning algorithm that can synthesize semantic regexes from a small number of positive and negative examples. Our proposed learning algorithm uses a combination of neural sketch generation and compositional type-directed synthesis for fast and effective generalization from a small number of examples. We have implemented these ideas in a new tool called Smore and evaluated it on representative data extraction tasks involving several textual datasets. Our evaluation shows that semantic regexes can better support complex data extraction tasks than standard regular expressions and that our learning algorithm significantly outperforms existing tools, including state-of-the-art neural networks and program synthesis tools.
41
Quek, Chai, Zaiyi Guo i Douglas L. Maskell. "A Novel Fuzzy Associative Memory Architecture for Stock Market Prediction and Trading". International Journal of Fuzzy System Applications 1, nr 1 (styczeń 2011): 61–78. http://dx.doi.org/10.4018/ijfsa.2011010105.
Pełny tekst źródłaStreszczenie:
In this paper, a novel stock trading framework based on a neuro-fuzzy associative memory (FAM) architecture is proposed. The architecture incorporates the approximate analogical reasoning schema (AARS) to resolve the problem of discontinuous (staircase) response and inefficient memory utilization with uniform quantization in the associative memory structure. The resultant structure is conceptually clearer and more computationally efficient than the Compositional Rule Inference (CRI) and Truth Value Restriction (TVR) fuzzy inference schemes. The local generalization characteristic of the associative memory structure is preserved by the FAM-AARS architecture. The prediction and trading framework exploits the price percentage oscillator (PPO) for input preprocessing and trading decision making. Numerical experiments conducted on real-life stock data confirm the validity of the design and the performance of the proposed architecture.
42
Pleshivtsev, Alexander. "The property of manufacturability of the architectural system as a component of a single and holistic composite solution". E3S Web of Conferences 135 (2019): 03025. http://dx.doi.org/10.1051/e3sconf/201913503025.
Pełny tekst źródłaStreszczenie:
Purpose: Analysis of modern methods (theory) of composition as a priority motivation of artistic and creative thinking in the process of architectural activity. Study of the influence of the complex properties of manufacturability on the nature of the formation of composite solutions of architectural systems. Methods and materials: dialectical approach, generally accepted logical research methods (analysis, system approach, generalization) and their synthesis using relevant information materials.Results: the basic means, regularities and principles of composition that determine the features of the formation of architectural systems are established. The analysis of the action of the basic (canonical) law of architectural composition and the conditions for the formation of a holistic and unified compositional solutions. The conceptual apparatus of the category (complex property) of “manufacturability” as a subject feature of the features of manufacturing, transportation, construction and operation of the architectural system is given. The direct nature of the interaction of “canonical” types (functional, constructive, artistic and aesthetic) and technological components in the tectonic display of the properties of the architectural system is established.Conclusions: Manufacturability of architectural systems formation is an equivalent component (in relation to the constructive, functional and artistic-aesthetic components) of a single and integral compositional solution. Indicators of the complex properties of manufacturability largely determine the functional quality of architectural systems.
43
Shutan, M. I. "On the two-part poems of F.I. Tyutchev’s". Literature at School, nr 4, 2020 (2020): 20–32. http://dx.doi.org/10.31862/0130-3414-2020-4-20-32.
Pełny tekst źródłaStreszczenie:
The article presents a typology of Tyutchev’s two-part poems, created on the basis of revealing the nature of semantic relations between their compositional elements. These are poems: 1) ith a philosophical or moral-psychological generalization in the second part, which does not just reform the content that is already clear to the reader, but reveals its meaning in the language of concepts and images (the implicit form and various variants of the explicit form: a common motif that binds the parts together; a dialogue; a chain of rhetorical questions; a persona’s consciousness, contemplating and ranking a lyrical character as the artistic center of the lyrical structure); 2) with the psychological gesture in the second part that conveys the desire of certain actions, able to change something in reality or in the inner world of the lyrical “I”; 3) with parallelism of human and nature, implemented mostly through the expanded comparison without, as a rule, a complete analogy (situation: the lyrical hero contemplates a particular material object – and an association with the world of the human soul comes to their mind); 4) with the contrast of objects of nature, its states, human and nature, life and death. In connection with the last point, it is specifically emphasized that one should not confuse the logic of contrast with contrast as a compositional technique. In the light of the analytical and interpretative operations, the following conclusion is made: all the types of relations between the two compositional elements, noted in the article, are represented by both symmetrical and asymmetric structures corresponding to different strophic forms, which allows us to speak about the flexibility of the poet’s artistic thinking, which finds different structural models for expressing the philosophical and moral-psychological content.
44
Крічлоу, К. В., О. В. Колосніченко, Т. В. Струмінська, Б. О. Процик i Б. В. Касс. "Виникнення стилів "байкер" і "рокер" у сучасній світовій моді". Art and Design, nr 4 (15.02.2021): 123–35. http://dx.doi.org/10.30857/2617-0272.2020.4.10.
Pełny tekst źródłaStreszczenie:
Study of the prerequisites of the emergence of Bikers and Rockers archetypes and their influence on the formation of corresponding subcultures and the direction of independent world fashion styles. The work uses a historical analysis and a visual-analytical method based on illustrative publications to study the artistic and compositional features of rider's clothing. Based on the scientific works of K. Jung, the influence of the collective unconscious on the process of the emergence of "bikers" and "rockers" subcultures are determined. The prerequisites at the inception of these styles were considered, the development of rider's clothing formation in world and Soviet’s fashion as artistic objects was studied, and the manifestations of compositional expressiveness were analysed. Scientific novelty consists in systematization of factors of occurrence of the classical biker style as an independent world fashion stream. Archetypical "bikers" and "rockers" have been identified and classified as part of subcultures and as a model of instinctive behaviour that exist in the collective unconscious. The practical significance consists in the analysis and theoretical generalization of materials that can be used in further applied scientific research of youth subcultures. The results are promising for further study of the influence of socially synthesized art on the clothing of drivers of motorized vehicles and on general trends in the development of world fashion.
45
Trapeznikova, Marina, Natalia Churbanova i Anastasia Lyupa. "Non-Isothermal Compositional Model for Simulation of Multiphase Porous Media Flows". EPJ Web of Conferences 224 (2019): 02010. http://dx.doi.org/10.1051/epjconf/201922402010.
Pełny tekst źródłaStreszczenie:
The research carried out in this work is aimed at the development of an explicit computational algorithm to simulate non-isothermal flow of multiphase multicomponent slightly compressible fluid through porous media. Such a modeling is necessary, for example, at solving practically important problems of hydrocarbon recovery via thermal methods and contaminated soil remediation via the hot steam injection. The original model and algorithm developed by the authors earlier draw the analogy with the quasi-gas-dynamic set of equations. Phase continuity equations were modified to get regularizing terms, while the type of equations was changed from parabolic to hyperbolic for the approximation by an explicit scheme with a mild enough stability condition. Since an adequate description of temperature-dependent porous media processes requires an explicit consideration of the transfer of mass and energy between the phases, the present work focuses on the generalization of the proposed approach to the case of multicomponent composition of fluids. Conservation laws are currently formulated for the components in terms of the mass concentrations of components in the phases. Constants of the phase equilibrium were used to close the set of equations. The developed model and algorithm have been verified numerically via test predictions of twoand three-phase flows, and, the phase transition of water into the gas phase at heating has been reproduced correctly.
46
Sarkar, Sahotra, Kelley A. Crews-Meyer, Kenneth R. Young, Christopher D. Kelley i Alexander Moffett. "A Dynamic Graph Automata Approach to Modeling Landscape Change in the Andes and the Amazon". Environment and Planning B: Planning and Design 36, nr 2 (1.01.2009): 300–318. http://dx.doi.org/10.1068/b33146.
Pełny tekst źródłaStreszczenie:
A generalization of cellular automata was developed that allows flexible, dynamic updating of variable neighborhood relationships, which in turn allows the integration of interactions at widely disparate spatial and temporal scales. Cells in the landscapes were modeled as vertices of dynamic graph automata that allow temporally variable causal connectivity between spatially nonadjacent cells. A trial was carried out to represent changes in an Amazonian and a tropical Andean landscape modeled as dynamic graph automata with input from a Landsat TM-derived Level 1 classification with the following classes: for the Amazon—forest, nonforest vegetation, water, and urban or bare (soil); for the Andes—forest, scrub (shrub or grassland), agriculture, and bare or exposed ground. Explicit automata transition rules were used to simulate temporal land-cover change. These rules were derived independently from fieldwork in each area, including vegetation plots or transects and informal interviews. Such a generalization of cellular automata was useful for modeling land-use–land-cover change (LULCC), although it potentially increases the computational complexity of an already data intensive process (involving 5–8 million cells, in 1000 stochastic simulations, with each simulation encompassing 15 annual time steps). The interannual predicted LULCC, while more nuanced in the Andean site, poses a serious threat to compositional and configurational stability in both the Andes and the Amazon, with implications for landscape heterogeneity and habitat fragmentation.
47
Tarasov, Volodymyr, i Veikie Wang. "The Category of Imagery in the Study of Fine Arts in China in the Second Half of the 20th — Early 21st Century: Chinese Art Discourse". Vìsnik Harkìvsʹkoi deržavnoi akademìi dizajnu ì mistectv 2022, nr 1 (15.01.2022): 107–16. http://dx.doi.org/10.33625/visnik2022.01.107.
Pełny tekst źródłaStreszczenie:
The article is devoted to the important problem of studying the imagery principles of fine art in China in the second half of the 20th — early 21st century. The focus is on the category of imagery. Today, this category is among the main ones within the research apparatus of Chinese art critics. Today the fine art of China has a very interesting art history ground; almost all the main vectors of Chinese art development need theoretical generalization. The categorical apparatus of research, which in many aspects differs from the conceptual and terminological discourse familiar to European scientists, is of great importance for the analysis of the development of Chinese art. Based on the analysis of a wide range of professional literature, which covers current research of the last decade (2012–2022), the authors of the article offer the following conclusions. Chinese scholars are actively using the traditional spectrum of art analysis: from the search for formal characteristics of works of art to the generalization of the system of imagery principles. In most cases, the category of imagery is interpreted as part of the axiological apparatus of art. This allows us to explain the essential features of the artistic idea of a work of art in relation to the properties of technical and compositional aspects. The main artistic elements that make up the content of the analytical apparatus include technical and technological, formal, compositional and plastic aspects of the analysis. They represent the “material” imagery nature of the work of art. According to research by Chinese scholars (including Fu Qiang, Jia Xiaodong, Zhang Chaohui, etc.), the system of means of expression is an integral part of the organization and expression of the artistic nature of art. At the same time, the interpretation of the artistic imagery of the work determines the “immaterial” (aesthetic and philosophical) nature of the evaluation of the work of art. It is often based on literary or religious reminiscences. In many studies, Chinese scholars have sought to show the direct relationship between two groups of artistic elements that generally make up the conceptual field of the imagery category.
48
Хиневич, Р. В., В. О. Скляренко i О. О. Слітюк. "PERSPECTIVE AS A MEANS OF COMPOSITIONAL EXPRESSIVENESS IN ARTISTIC PHOTOGRAPHY". Art and Design, nr 3 (3.02.2023): 9–18. http://dx.doi.org/10.30857/2617-0272.2022.3.1.
Pełny tekst źródłaStreszczenie:
The aim: determination of the features of the use of perspective in artistic photography as a means of compositional expressiveness. Analysis of geometric and optical aspects of the visual characteristics of different types of perspective in photographic art.
Methodology. A comparative analysis of compositional methods of conveying volume and depth of space in artistic photography is applied. Methods of systematization and generalization were used to determine the specific features of different types of perspective in photo art.
Results. The peculiarities of the concept of perspective in photography are considered. The common features of works of painting and photo art in the context of conveying the depth and volume of the depicted space are determined. The analysis of the main types of perspective – linear, tonal, aerial, optical and spherical – was performed, using the example of their use in artistic photography. The influence of the perspective construction of the picture on the visual perception of the image and its content is determined. The role of technical means and their parameters in constructing the perspective of a photographic frame is clarified.
Scientific novelty. The main methods of displaying the volume and depth of space in a photo image when using different types of perspective are defined. The geometric and optical regularities of perspective as a pictorial means in art photography are revealed.
Practical significance. Information on the use of different types of perspective in artistic photography has been studied and systematized. Recommendations are provided for the selection of geometric and optical parameters of the frame for the transmission of visual information in works of photographic art. The obtained results can be used in the educational process in the preparation of bachelors specializing in photo-video design.
49
Tang, Yiming, i Fuji Ren. "Variable Differently Implicational Inference for R- and S-Implications". International Journal of Information Technology & Decision Making 15, nr 05 (wrzesień 2016): 1235–64. http://dx.doi.org/10.1142/s0219622016500334.
Pełny tekst źródłaStreszczenie:
As a generalization of the compositional rule of inference (CRI) algorithm and the fully implicational algorithm, the differently implicational algorithm of fuzzy inference not only inherit the advantages of the fully implicational algorithm, but also has stronger practicability. Then, the variable differently implicational algorithm was proposed to make the current differently implicational algorithms compose a united whole. In this paper, the variable differently implicational algorithm is further researched focusing on the fuzzy modus tollens (FMT) problem. The differently implicational principle for FMT is improved. Moreover, the unified solutions of the variable differently implicational algorithm for FMT are accomplished for R- and S-implications. Following that, as an important index of fuzzy inference, the continuity of this algorithm is analyzed for main R- and S-implications, in which excellent performance is obtained. Finally, its optimal solutions as well as inference examples are provided for several specific R- and S-implications.
50
DAVIDOVICH, А., T. DAVIDOVICH i A. KREMNEVA. "FEATURES OF THE ARCHITECTURAL AND COMPOSITIONAL SOLUTION OF THE CHURCH IN THE VILLAGE OF SOLY". Herald of Polotsk State University. Series F. Civil engineering. Applied sciences 32, nr 14 (29.12.2022): 10–15. http://dx.doi.org/10.52928/2070-1683-2022-32-14-10-15.
Pełny tekst źródłaStreszczenie:
The article examines and analytically evaluates the features of the architectural and spatial organization and compositional structure of the Catholic cult object of the 20th century, the principles and methods of shaping which do not fit into the format of traditional canons and parameters of architectural solutions of churches. Being, due to its unusual figurative characteristics, the object of attraction of numerous tourists, the Church of Our Lady of Ruzhentsova in the village of Soly, Grodno region, nevertheless, unfairly, in our opinion, is deprived of the attention of professional specialists-architects. Apart from brief information in Wikipedia, commercials on the Internet, as well as stingy information in some literary sources, it was not possible to find any serious studies of the architectural features of the unique object. At the same time, there are discrepancies in the assessment of his style affiliation – modern, neo-Baroque, non-Gothic? In the work, based on a detailed study and generalization of literary sources, Internet resources and visual field survey, the author's version regarding the stylistic affiliation of this object is proposed.