Journal articles: 'Generative approach'

1

Sobirovich, Sukhrob Avezov. "A PRAGMATICALLY ORIENTED APPROACH TO GENERATIVE LINGUISTICS." Current Research Journal of Philological Sciences 5, no. 4 (2024): 69–75. http://dx.doi.org/10.37547/philological-crjps-05-04-12.

Full text

Abstract:

The annotated paper examines the possibility of creating an original grammatical system when teaching a new language. The pragmatic approach to generative linguistics was the methodology of language acquisition using a unified model of the Russian sentence. The article discusses algorithms of sentence modelling at two levels: external and internal, based on the theories of N.Chomsky and L.Teniers. The external level includes the construction of a unified sentence structure from the deep structure to the surface structure according to N.Chomsky. And the internal level includes the structural correlation of model elements as the content of the unified sentence structure itself -according to L.Tenier. The theories of N.Chomsky and L.Teniers defined all models as a union of components and reflected in the same models the relations of hierarchy between the components. The study demonstrates a way of teaching foreign speakers the language with the help of the author’s theory of algorithmic syntax.

APA, Harvard, Vancouver, ISO, and other styles

2

Victor Parque, Masakazu Kobayashi, and Masatake Higashi. "3105 A Generative Approach to Wire Harness Design." Proceedings of Design & Systems Conference 2013.23 (2013): _3105–1_—_3105–2_. http://dx.doi.org/10.1299/jsmedsd.2013.23._3105-1_.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Wong, Alexander, Mohammad Javad Shafiee, Brendan Chwyl, and Francis Li. "GenSynth: a generative synthesis approach to learning generative machines for generate efficient neural networks." Electronics Letters 55, no. 18 (2019): 986–89. http://dx.doi.org/10.1049/el.2019.1719.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Yang, Chi Bok, and Yang Sok Kim. "Implementation of Retrieval Augmented Generation (RAG) Model Using LLM: A RapidMiner-Based Approach." Korean Institute of Smart Media 14, no. 2 (2025): 34–42. https://doi.org/10.30693/smj.2025.14.2.34.

Full text

Abstract:

Generative AI technology, driven by Large Language Models (LLMs), is being increasingly utilized to overcome existing limitations. Retrieval-Augmented Generation (RAG) has emerged as an effective approach to reduce hallucination in LLMs by leveraging up-to-date and domain-specific knowledge beyond training data. However, most studies propose programming-based implementations. This research introduces a GUI-based RAG framework using RapidMiner, to construct RAG systems without programming proficiency. The methodology includes storing and retrieving embeddings with the Qdrant vector database and generating question-and-answer pairs via the OpenAI API. Practical demonstrations confirm the system’s effectiveness in real-world scenarios, offering a simpler and more efficient method for developing generative AI services with LLMs.

APA, Harvard, Vancouver, ISO, and other styles

5

Sinha, Himanshu. "The Identification of Network Intrusions with Generative Artificial Intelligence Approach for Cybersecurity." Journal of Web Applications and Cyber Security 2, no. 2 (2024): 20–29. http://dx.doi.org/10.48001/jowacs.2024.2220-29.

Full text

Abstract:

Generative Artificial Intelligence (Generative AI) offers a paradigm shift to the way robots perceive and interact with data. Generative AI approaches aim to produce new data samples that closely match the original dataset, in contrast to standard AI models that concentrate on tasks such as categorisation or prediction. This ability has broad implications for a variety of fields, including network security. New generation of network intrusion defense brought forth by Generative AI is revolution using the area of network security. In this work, investigates the revolutionary potential of Generative AI in network intrusion detection, with the goal of developing a proactive and adaptable cyber protection mechanism. In this work the use of Generative AI use for identifying network intrusions, using the NSL-KDD dataset. The work begins with meticulous data preprocessing using handling missing values, encoding, feature scaling, and feature extraction to enhance the dataset and then focuses on using Generative AI for intrusion detection. In this work many models have been used like SVM, AE, DAE, and GANs, and in this GANs has the best accuracy with 91.12% compared with other models.

APA, Harvard, Vancouver, ISO, and other styles

6

Thorp, H. Holden. "Generative approach to research integrity." Science 381, no. 6658 (2023): 587. http://dx.doi.org/10.1126/science.adk1852.

Full text

Abstract:

It’s been a bad few weeks for public perceptions of research integrity, as multiple cases at elite universities have received wide news coverage. Francesca Gino, a scientist at Harvard University, is in a legal dispute over whether data in newly retracted papers about dishonesty were manipulated; she is now suing Harvard and the researchers who surfaced the alleged problems. Likewise, Duke University is investigating published work by scientist Daniel Ariely. Johns Hopkins University may initiate an investigation of research misconduct by Nobel laureate Gregg Semenza. And most prominently, the president of Stanford University, Marc Tessier-Lavigne, recently resigned after the institution’s report determined that the “culture” in his laboratory contributed to manipulation of results.

APA, Harvard, Vancouver, ISO, and other styles

7

Kumar Jana, Aryyama, Srija Saha, and Arnab Dey. "DyGAISP: Generative AI-Powered Approach for Intelligent Software Lifecycle Planning." International Journal of Science and Research (IJSR) 13, no. 5 (2024): 1275–82. http://dx.doi.org/10.21275/sr24520092232.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Yüksel, Nurullah, and Hüseyin Rıza Börklü. "A Generative Deep Learning Approach for Improving the Mechanical Performance of Structural Components." Applied Sciences 14, no. 9 (2024): 3564. http://dx.doi.org/10.3390/app14093564.

Full text

Abstract:

This study aimed to improve the mechanical properties of 3D concept designs by combining the design capability of a generative adversarial network with finite element analysis. This approach offers an innovative perspective on the conditioning of generative models while improving design properties and automation. A new design and evaluation framework has been developed for GAN models to generate 3D models with improved mechanical properties. The framework is an iterative process that includes dataset generation, GAN training, and finite element analysis. A “joint” component used in the aerospace industry is considered to demonstrate the proposed method’s effectiveness. Over six iterations, an increase of 20% is recorded in the average safety factor of the designs, and the variety of designs produced is narrowed in the desired direction. These findings suggest that the direct generation of structural components with generative models can expand the potential of deep learning in engineering design. Another innovative aspect of this study is that it provides a new option for the conditioning of data-dependent generative design models.

APA, Harvard, Vancouver, ISO, and other styles

9

Regol, Florence, and Mark Coates. "Diffusing Gaussian Mixtures for Generating Categorical Data." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 8 (2023): 9570–78. http://dx.doi.org/10.1609/aaai.v37i8.26145.

Full text

Abstract:

Learning a categorical distribution comes with its own set of challenges. A successful approach taken by state-of-the-art works is to cast the problem in a continuous domain to take advantage of the impressive performance of the generative models for continuous data. Amongst them are the recently emerging diffusion probabilistic models, which have the observed advantage of generating high-quality samples. Recent advances for categorical generative models have focused on log likelihood improvements. In this work, we propose a generative model for categorical data based on diffusion models with a focus on high-quality sample generation, and propose sampled-based evaluation methods. The efficacy of our method stems from performing diffusion in the continuous domain while having its parameterization informed by the structure of the categorical nature of the target distribution. Our method of evaluation highlights the capabilities and limitations of different generative models for generating categorical data, and includes experiments on synthetic and real-world protein datasets.

APA, Harvard, Vancouver, ISO, and other styles

10

Wang, Yunpeng, Meng Pang, Shengbo Chen, and Hong Rao. "Consistency-GAN: Training GANs with Consistency Model." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 14 (2024): 15743–51. http://dx.doi.org/10.1609/aaai.v38i14.29503.

Full text

Abstract:

For generative learning tasks, there are three crucial criteria for generating samples from the models: quality, coverage/diversity, and sampling speed. Among the existing generative models, Generative adversarial networks (GANs) and diffusion models demonstrate outstanding quality performance while suffering from notable limitations. GANs can generate high-quality results and enable fast sampling, their drawbacks, however, lie in the limited diversity of the generated samples. On the other hand, diffusion models excel at generating high-quality results with a commendable diversity. Yet, its iterative generation process necessitates hundreds to thousands of sampling steps, leading to slow speeds that are impractical for real-time scenarios. To address the aforementioned problem, this paper proposes a novel Consistency-GAN model. In particular, to aid in the training of the GAN, we introduce instance noise, which employs consistency models using only a few steps compared to the conventional diffusion process. Our evaluations on various datasets indicate that our approach significantly accelerates sampling speeds compared to traditional diffusion models, while preserving sample quality and diversity. Furthermore, our approach also has better model coverage than traditional adversarial training methods.

APA, Harvard, Vancouver, ISO, and other styles

11

Zou, Jincheng, Guorong Chen, Jian Wang, Bao Zhang, Hong Hu, and Cong Liu. "A Hierarchical Latent Modulation Approach for Controlled Text Generation." Mathematics 13, no. 5 (2025): 713. https://doi.org/10.3390/math13050713.

Full text

Abstract:

Generative models based on Variational Autoencoders (VAEs) represent an important area of research in Controllable Text Generation (CTG). However, existing approaches often do not fully exploit the potential of latent variables, leading to limitations in both the diversity and thematic consistency of the generated text. To overcome these challenges, this paper introduces a new framework based on Hierarchical Latent Modulation (HLM). The framework incorporates a hierarchical latent space modulation module for the generation and embedding of conditional modulation parameters. By using low-rank tensor factorization (LMF), the approach combines multi-layer latent variables and generates modulation parameters based on conditional labels, enabling precise control over the features during text generation. Additionally, layer-by-layer normalization and random dropout mechanisms are employed to address issues such as the under-utilization of conditional information and the collapse of generative patterns. We performed experiments on five baseline models based on VAEs for conditional generation, and the results demonstrate the effectiveness of the proposed framework.

APA, Harvard, Vancouver, ISO, and other styles

12

Mahajan, Bhushan, Deven waykar, Aditya Kadam, Vaishnavi Bhagde, and Prof S. R. Nalamwar. "Enhancing the Concept of Generative Art." International Journal for Research in Applied Science and Engineering Technology 11, no. 1 (2023): 1586–92. http://dx.doi.org/10.22214/ijraset.2023.48877.

Full text

Abstract:

Abstract: Art that was entirely or partially produced by an autonomous system is referred to as generative art. An autonomous system is typically a non-human entity that is capable of making judgments on its own about aspects of a piece of art that would otherwise require direct input from the artist. We have created a GUI which lists the applications which are based on the concept of generative art. Our GUI contains applications like random password generation, abstract artworks, map generation, wallpaper generation. Password generator will provide randomly generated passwords which would be derived from the images created using image generation algorithms/scripts such as EPWT and python’s in-built random function which uses algorithms like mersenne twister, a pseudo-random number generator. This application aims to provide usefulness for old hashing algorithms which are getting obsolete day by day. Abstract artwork generator will generate random images for stimulating creativity of artists, designers, architectural and marketing firms for getting started on a new project. This generator uses general complex functions which contain scripts for different shapes and combinations. This approach is able to generate some innovative solutions and demonstrates the power of computational approach. A layout of the area with the requested coordinates and different constraints will be provided through map generating model. Wallpaper generation model will generate aesthetically pleasing wallpapers with adjustable features.

APA, Harvard, Vancouver, ISO, and other styles

13

Xu, Chenglong, Peidong Xu, Yuxin Dai, et al. "A Two-Stage Generative Architecture for Renewable Scenario Generation Based on Temporal Scenario Representation and Diffusion Models." Energies 18, no. 5 (2025): 1275. https://doi.org/10.3390/en18051275.

Full text

Abstract:

Scenario generation proves to be an effective approach for addressing uncertainties in stochastic programming for power systems with integrated renewable resources. In recent years, numerous studies have explored the application of deep generative models to scenario generation. Considering the challenge of characterizing renewable resource uncertainty, in this paper, we propose a novel two-stage generative architecture for renewable scenario generation using diffusion models. Specifically, in the first stage the temporal features of the renewable energy output are learned and encoded into the hidden space by means of a representational model with an encoder–decoder structure, which provides the inductive bias of the scenario for generation. In the second stage, the real distribution of vectors in the hidden space is learned based on the conditional diffusion model, and the generated scenario is obtained through decoder mapping. The case study demonstrates the effectiveness of this architecture in generating high-quality renewable scenarios. In comparison to advanced deep generative models, the proposed method exhibits superior performance in a comprehensive evaluation.

APA, Harvard, Vancouver, ISO, and other styles

14

Joshi, Ameya, Minsu Cho, Viraj Shah, et al. "InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 4377–84. http://dx.doi.org/10.1609/aaai.v34i04.5863.

Full text

Abstract:

Generative Adversarial Networks (GANs), while widely successful in modeling complex data distributions, have not yet been sufficiently leveraged in scientific computing and design. Reasons for this include the lack of flexibility of GANs to represent discrete-valued image data, as well as the lack of control over physical properties of generated samples. We propose a new conditional generative modeling approach (InvNet) that efficiently enables modeling discrete-valued images, while allowing control over their parameterized geometric and statistical properties. We evaluate our approach on several synthetic and real world problems: navigating manifolds of geometric shapes with desired sizes; generation of binary two-phase materials; and the (challenging) problem of generating multi-orientation polycrystalline microstructures.

APA, Harvard, Vancouver, ISO, and other styles

15

Čučaković, Aleksandar, Biljana Jović, and Mirjana Komnenov. "Biomimetic Geometry Approach to Generative Design." Periodica Polytechnica Architecture 47, no. 2 (2016): 70–74. http://dx.doi.org/10.3311/ppar.10082.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Jager, Gottfried. "Generative Photography: A Systematic, Constructive Approach." Leonardo 19, no. 1 (1986): 19. http://dx.doi.org/10.2307/1578296.

Full text

APA, Harvard, Vancouver, ISO, and other styles

17

Schneider, Julia, Sanae Essafi, Ana Pilar Valerga Puerta, and Diana Völz. "Comprehensive Generative Approach to Design Insoles." Current Directions in Biomedical Engineering 10, no. 4 (2024): 555–58. https://doi.org/10.1515/cdbme-2024-2136.

Full text

Abstract:

Abstract Orthopaedic insoles are necessary for correcting foot deformities and providing customized support. This paper investigates the optimization of insole design through computational methods, with a focus on generative design (GD) techniques. By integrating advanced design methods with biomechanical analysis, this study aims to develop customized insoles that effectively treat foot disorders. To adequately account for all relevant forces acting on the foot during gait, a biomechanical load model is created. In addition to vertical forces, the model includes horizontal forces (anterior-posterior and medial-lateral) that occur parallel to the walking surface. GD can optimize the insole design to distribute pressure and support areas of the foot appropriately by creating functionally graded lattice structures. The study examines the potential of GD in creating insoles and the impact of the load model on the design outcome. The design process includes dynamic pedography and gait analysis to ensure that the insoles are tailored to the patient’s individual needs. Future research challenges include incorporating horizontal forces and minimizing mass while maintaining support. The study highlights the potential of computational methods, such as GD and artificial intelligence, in optimizing the design of orthopaedic insoles to ultimately improve patient comfort and mobility.

APA, Harvard, Vancouver, ISO, and other styles

18

TARASIUK, Anna, Inna PYLYPENKO, and Nataliia BEREHOVENKO. "GENERATIVE APPROACH OF SENTENCE STRUCTURE ANALYSIS." Humanities science current issues 3, no. 72 (2024): 199–204. http://dx.doi.org/10.24919/2308-4863/72-3-29.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Asperti, Andrea, Salvatore Fiorilla, and Lorenzo Orsini. "A Generative Approach to Person Reidentification." Sensors 24, no. 4 (2024): 1240. http://dx.doi.org/10.3390/s24041240.

Full text

Abstract:

Person Re-identification is the task of recognizing comparable subjects across a network of nonoverlapping cameras. This is typically achieved by extracting from the source image a vector of characteristic features of the specific person captured by the camera. Learning a good set of robust, invariant and discriminative features is a complex task, often leveraging contrastive learning. In this article, we explore a different approach, learning the representation of an individual as the conditioning information required to generate images of the specific person starting from random noise. In this way we decouple the identity of the individual from any other information relative to a specific instance (pose, background, etc.), allowing interesting transformations from one identity to another. As generative models, we use the recent diffusion models that have already proven their sensibility to conditioning in many different contexts. The results presented in this article serve as a proof-of-concept. While our current performance on common benchmarks is lower than state-of-the-art techniques, the approach is intriguing and rich of innovative insights, suggesting a wide range of potential improvements along various lines of investigation.

APA, Harvard, Vancouver, ISO, and other styles

20

Arunkumar, A., A. Sooriyamoorthy, C. Mishael, and A. Giri. "A study on engine piston optimization by generative design approach." IOP Conference Series: Materials Science and Engineering 1228, no. 1 (2022): 012014. http://dx.doi.org/10.1088/1757-899x/1228/1/012014.

Full text

Abstract:

Abstract Significant enterprises today favor the cooperation of generative plans in the manufacturing and assembling departments. Therefore our aim is to dwell on the more straightforward degrees of generative design to demonstrate the modification of boundary conditions and properties to exhibit modern applications. Generative Design has demonstrated to be a significant upgrade in the machine-producing side of the business because of the simplicity in changes, higher resilience, and reduced number of faults that arise. Nevertheless owing to the added complex shape of structures, the model generation and design are posed with challenges. This paper involves the examination and generative design of a 4-Stroke engine piston. The proposed method is validated through a study which closely resembles a real life prototype. The examination aims to dissect and detail a newly formed design grid for the current cylinder of the F20C 4 - stroke 4 - cylinder engine at the core of the Honda S2000. Our aim to study on piston design, which makes it lighter and more efficient while keeping the similar volume yield in the cylinder. The paper depicts the process of optimizing the component through mass reduction where the mass was reduced by close to twenty three percent.

APA, Harvard, Vancouver, ISO, and other styles

21

Coorey, Benjamin P., and Julie R. Jupp. "Generative spatial performance design system." Artificial Intelligence for Engineering Design, Analysis and Manufacturing 28, no. 3 (2014): 277–83. http://dx.doi.org/10.1017/s0890060414000225.

Full text

Abstract:

AbstractArchitectural spatial design is a wicked problem that can have a multitude of solutions for any given brief. The information needed to resolve architectural design problems is often not readily available during the early conceptual stages, requiring proposals to be evaluated only after an initial solution is reached. This “solution-driven” design approach focuses on the generation of designs as a means to explore the solution space. Generative design can be achieved computationally through parametric and algorithmic processes. However, utilizing a large repertoire of organiational patterns and design precedent knowledge together with the precise criteria of spatial evaluation can present design challenges even to an experienced architect. In the implementation of a parametric design process lies an opportunity to supplement the designer's knowledge with computational decision support that provides real-time spatial feedback during conceptual design. This paper presents an approach based on a generative multiperformance framework, configured for generating and optimizing architectural designs based on a precedent design. The system is constructed using a parametric modeling environment enabling the capture of precedent designs, extraction of spatial analytics, and demonstration of how populations can be used to drive the generation and optimization of alternate spatial solutions. A pilot study implementing the complete workflow of the system is used to illustrate the benefits of coupling parametric modeling with structured precedent analysis and design generation.

APA, Harvard, Vancouver, ISO, and other styles

22

Wu, Zhonghua, Wenzhong Yang, Meng Zhang, Fuyuan Wei, and Xinfang Liu. "A Reinforcement Learning-Based Generative Approach for Event Temporal Relation Extraction." Entropy 27, no. 3 (2025): 284. https://doi.org/10.3390/e27030284.

Full text

Abstract:

Event temporal relation extraction is a crucial task in natural language processing, aimed at recognizing the temporal relations between event triggers in a text. Despite extensive efforts in this area, the existing methods face two main issues. Firstly, the previous models for event temporal relation extraction mainly rely on a classification framework, which fails to output the crucial contextual words necessary for predicting the temporal relations between two event triggers. Secondly, the prior research that formulated natural language processing tasks as text generation problems usually trained the generative models by maximum likelihood estimation. However, this approach encounters potential difficulties when the optimization objective is misaligned with the task performance metrics. To resolve these limitations, we introduce a reinforcement learning-based generative framework for event temporal relation extraction. Specifically, to output the important contextual words from the input sentence for temporal relation identification, we introduce dependency path generation as an auxiliary task to complement event temporal relation extraction. This task is solved alongside temporal relation prediction to enhance model performance. To achieve this, we reformulate the event temporal relation extraction task as a text generation problem, aiming to generate both event temporal relation labels and dependency path words based on the input sentence. To bridge the gap between the optimization objective and task performance metrics, we employ the REINFORCE algorithm to optimize our generative model, designing a novel reward function to simultaneously capture the accuracy of temporal prediction and the quality of generation. Lastly, to mitigate the high variance issue encountered when using the REINFORCE algorithm in multi-task generative model training, we propose a baseline policy gradient algorithm to improve the stability and efficiency of the training process. Experimental results on two widely used datasets, MATRES and TB-DENSE, show that our approach exhibits competitive performance.

APA, Harvard, Vancouver, ISO, and other styles

23

Mohapatra, Mayesh, Anshumaan Phukan, and Vijay K. Madisetti. "Generative Adversarial Network Based Approach towards Synthetically Generating Insider Threat Scenarios." Journal of Software Engineering and Applications 16, no. 11 (2023): 586–604. http://dx.doi.org/10.4236/jsea.2023.1611030.

Full text

APA, Harvard, Vancouver, ISO, and other styles

24

Bahadur Singh, Rudrendra. "A Generative Approach to Argument Structure Extraction." INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 05 (2025): 1–9. https://doi.org/10.55041/ijsrem47073.

Full text

Abstract:

Abstract The goal of argument mining, or AM, is to identify the argumentative structures in a document. Prior approaches necessitate a number of subtasks, including component classification, relation classification, and span identification. Therefore, rule-based postprocessing is required for these methods to extract generative structures from each subtask's output. This method increases the model's complexity and broadens the hyperparameter search space. We suggest a straightforward yet effective technique based on a text-to-text generation strategy employing a pretrained encoder-decoder language model to overcome this challenge. Our approach eliminates the requirement for task-specific postprocessing and hyperparameter optimisation by producing argumentatively annotated text for spans, components, and relations all at once. Additionally, as it is a simple text-to-text creation method, we may readily modify our strategy to fit different kinds of argumentative frameworks. Experimental findings show that our strategy works well, achieving state-of-the-art performance on three distinct benchmark datasets: the Cornell eRulemaking Cor- pus (CDCP), AbstRCT and the Argument-annotated Essays Corpus (AAEC). Keywords: Argument Mining, Text-to-Text Generation, T5

APA, Harvard, Vancouver, ISO, and other styles

25

Andreia, Gabriela Andrei, Mațcu-Zaharia Mara, and Florentin Mariciuc Dragoș. "Ready to Grip AI's Potential? Insights from an Exploratory Study on Perceptions of Human-AI Collaboration." BRAIN. Broad Research in Artificial Intelligence and Neuroscience 15, no. 2 (2024): 01–22. https://doi.org/10.18662/brain/15.2/560.

Full text

Abstract:

One of the emerging technologies arising with Industry 4.0 is generative artificial intelligence (AI). Despite its disruptive nature and controversies, the effective and ethical use of AI is increasingly preoccupying organizations of all sizes as well as their employees. Focusing on generative AI, this paper presents findings from a qualitative study that provides insights into how Generation Z, the newest workforce, perceives human-AI collaboration. Based on in-depth interviews and a micro-meso-macro approach, the study reveals a dual perspective. Participants recognized the advantages AI brings, such as increased efficiency, productivity, and information availability. However, they were concerned about various risks such as: technology addiction, job loss, data privacy and ethical issues. At the micro level, generative AI was seen as beneficial for providing information and inspiration, but over-reliance could limit people's skills and create dependency. At the meso, organizational level, it could increase efficiency and productivity, but potentially replace jobs. At the macro, societal level, generative AI could support innovation but risks dehumanizing communication and relationships. Data privacy and ethics concerns were expressed at all three levels, indicating that a combination of institutional safeguards and awareness of data privacy and ethics at all levels is required to achieve the full benefits of generative AI. This would help organisations to capitalise on technological advances and support the development of ethical use of AI tools.

APA, Harvard, Vancouver, ISO, and other styles

26

Blaschke, Thomas, and Jürgen Bajorath. "Compound dataset and custom code for deep generative multi-target compound design." Future Science OA 7, no. 6 (2021): FSO715. http://dx.doi.org/10.2144/fsoa-2021-0033.

Full text

Abstract:

Aim: Generating a data and software infrastructure for evaluating multi-target compound (MT-CPD) design via deep generative modeling. Methodology: The REINVENT 2.0 approach for generative modeling was extended for MT-CPD design and a large benchmark data set was curated. Exemplary results & data: Proof-of-concept for deep generative MT-CPD design was established. Custom code and the benchmark set comprising 2809 MT-CPDs, 61,928 single-target and 295,395 inactive compounds from biological screens are made freely available. Limitations & next steps: MT-CPD design via deep learning is still at its conceptual stages. It will be required to demonstrate experimental impact. The data and software we provide enable further investigation of MT-CPD design and generation of candidate molecules for experimental programs.

APA, Harvard, Vancouver, ISO, and other styles

27

Chang, Yeong-Hwa, Pei-Hua Chung, Yu-Hsiang Chai, and Hung-Wei Lin. "Color Face Image Generation with Improved Generative Adversarial Networks." Electronics 13, no. 7 (2024): 1205. http://dx.doi.org/10.3390/electronics13071205.

Full text

Abstract:

This paper focuses on the development of an improved Generative Adversarial Network (GAN) specifically designed for generating color portraits from sketches. The construction of the system involves using a GPU (Graphics Processing Unit) computing host as the primary unit for model training. The tasks that require high-performance calculations are handed over to the GPU host, while the user host only needs to perform simple image processing and use the model trained by the GPU host to generate images. This arrangement reduces the computer specification requirements for the user. This paper will conduct a comparative analysis of various types of generative networks which will serve as a reference point for the development of the proposed Generative Adversarial Network. The application part of the paper focuses on the practical implementation and utilization of the developed Generative Adversarial Network for the generation of multi-skin tone portraits. By constructing a face dataset specifically designed to incorporate information about ethnicity and skin color, this approach can overcome a limitation associated with traditional generation networks, which typically generate only a single skin color.

APA, Harvard, Vancouver, ISO, and other styles

28

Vranic, Valentino, and Roman Táborský. "Features as transformations: A generative approach to software development." Computer Science and Information Systems 13, no. 3 (2016): 759–78. http://dx.doi.org/10.2298/csis160128027v.

Full text

Abstract:

The objective of feature modeling is to foster software reuse by enabling to explicitly and abstractly express commonality and variability in the domain. Feature modeling is used to configure other models and, eventually, code. These software assets are being configured by the feature model based on the selection of variable features. However, selecting a feature is far from a naive component based approach where feature inclusion would simply mean including the corresponding component. More often than not, feature inclusion affects several places in models or code to be configured requiring their nontrivial adaptation. Thus, feature inclusion recalls transformation and this is at heart of the approach to feature model driven generation of software artifacts proposed in this paper. Features are viewed as transformations that may be executed during the generative process conducted by the feature model configuration. The generative process is distributed in respective transformations enabling the developers to have a better control over it. This approach can be applied to modularize changes in product customization and to establish generative software product lines by gradual refactoring of existing products.

APA, Harvard, Vancouver, ISO, and other styles

29

Belov, Boris, and Peter Panfilov. "Generative AI-based Approach to Concept Drift Generation in Streaming Text Data." WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS 22 (October 21, 2024): 11–20. https://doi.org/10.37394/23209.2025.22.2.

Full text

Abstract:

Real-time analysis of text streams is crucial for industrial and business processes and scenarios. It is expected to be one of the important future research topics in the text processing and understanding domain. Analysis of text data is based on the use of pre-trained machine learning/data mining (ML/DM) models that may demonstrate performance degradation over time due to the drift in text data. The problem of tracking drift in data and quickly retraining a model in response to changes in the operational environment represents a great challenge in product model environments. We discuss and evaluate an approach to artificially generating concept drift aimed at providing test data for evaluating model performance and improving its accuracy. Existing methods for generating concept drift in text streams are limited to specific domains and are not universally applicable. This paper explores approaches for generating concept drift in text streams using the latest developments in generative artificial intelligence (GenAI) such as Large Language Models (LLMs). Two methods for generating concept drift with LLMs are proposed and compared to existing techniques. The comparison demonstrates that concept drift generation using LLMs is more effective than traditional methods. Additionally, LLMs can rapidly produce complex concept drift scenarios that are significantly more challenging to generate with standard approaches.

APA, Harvard, Vancouver, ISO, and other styles

30

Raposo, Adriano N., and Vasco N. G. J. Soares. "Generative Jazz Chord Progressions: A Statistical Approach to Harmonic Creativity." Information 16, no. 6 (2025): 504. https://doi.org/10.3390/info16060504.

Full text

Abstract:

Jazz music has long been a subject of interest in the field of generative music. Traditional jazz chord progressions follow established patterns that contribute to the genre’s distinct sound. However, the demand for more innovative and diverse harmonic structures has led to the exploration of alternative approaches in music generation. This paper addresses the challenge of generating novel and engaging jazz chord sequences that go beyond traditional chord progressions. It proposes an unconventional statistical approach, leveraging a corpus of 1382 jazz standards, which includes key information, song structure, and chord sequences by section. The proposed method generates chord sequences based on statistical patterns extracted from the corpus, considering a tonal context while introducing a degree of unpredictability that enhances the results with elements of surprise and interest. The goal is to move beyond conventional and well-known jazz chord progressions, exploring new and inspiring harmonic possibilities. The evaluation of the generated dataset, which matches the size of the learning corpus, demonstrates a strong statistical alignment between distributions across multiple analysis parameters while also revealing opportunities for further exploration of novel harmonic pathways.

APA, Harvard, Vancouver, ISO, and other styles

31

Virah Sawmy, Malika, Pierre Golbach, and Christina Tewes-Gradl. "Generative Evaluation." Journal of Awareness-Based Systems Change 4, no. 2 (2024): 131–50. https://doi.org/10.47061/jasc.v4i2.7773.

Full text

Abstract:

Evaluation has so much potential for learning, co-creation, and collaboration around more inclusive and regenerative programs and, ultimately, systems. Yet, currently, evaluations are often experienced as controlling and frustrating add-ons. Inspired by developmental evaluation, we have experimented with generative methods to make evaluation a space for stakeholders to come together, re-connect, re-fresh the purpose of collaboration and re-view the design. We see that such a generative approach to evaluation can help to (1) express and co-construct systemic issues that often remain hidden and destructive otherwise, (2) create connection and energy for collaboration and (3) open a world of possibilities to learn from the past and adjust for the future. Organizations that use a more generative approach can hope to change the mindset within to more learning, collaboration, and courageous experimentation.

APA, Harvard, Vancouver, ISO, and other styles

32

Patarakin, Yevgeny D., and Boris B. Yarmakhov. "Data farming for virtual school laboratories." RUDN Journal of Informatization in Education 18, no. 4 (2021): 347–59. http://dx.doi.org/10.22363/2312-8631-2021-18-4-347-359.

Full text

Abstract:

Problem and goal. Building statistical, mathematical, computational and research literacies in teaching school subjects is discussed in the article. The purpose is to develop a model for generating data for research experiments by students. Methodology. The Netlogo data generation and consecutive statistical data procession in CODAP and R programming language were used. Results. The generative approach helps students to work with data collected by agents, programmed by students themselves. In doing so, the student assumes the position of a researcher, who plans an experiment and analyses its results. Conclusion. The proposed approach of data generation and analysis allows to introduce the student to the contemporary culture of generating and sharing data.

APA, Harvard, Vancouver, ISO, and other styles

33

Theodorou, Brandon, Shrusti Jain, Cao Xiao, and Jimeng Sun. "ConSequence: Synthesizing Logically Constrained Sequences for Electronic Health Record Generation." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 14 (2024): 15355–63. http://dx.doi.org/10.1609/aaai.v38i14.29460.

Full text

Abstract:

Generative models can produce synthetic patient records for analytical tasks when real data is unavailable or limited. However, current methods struggle with adhering to domain-specific knowledge and removing invalid data. We present ConSequence, an effective approach to integrating domain knowledge into sequential generative neural network outputs. Our rule-based formulation includes temporal aggregation and antecedent evaluation modules, ensured by an efficient matrix multiplication formulation, to satisfy hard and soft logical constraints across time steps. Existing constraint methods often fail to guarantee constraint satisfaction, lack the ability to handle temporal constraints, and hinder the learning and computational efficiency of the model. In contrast, our approach efficiently handles all types of constraints with guaranteed logical coherence. We demonstrate ConSequence's effectiveness in generating electronic health records, outperforming competitors in achieving complete temporal and spatial constraint satisfaction without compromising runtime performance or generative quality. Specifically, ConSequence successfully prevents all rule violations while improving the model quality in reducing its test perplexity by 5% and incurring less than a 13% slowdown in generation speed compared to an unconstrained model.

APA, Harvard, Vancouver, ISO, and other styles

34

Láng, Blanka, and Balázs Dömsödi. "Integration of AI and Metaheuristics in Educational Software: A Hybrid Approach to Exercise Generation." International Journal of Emerging Technologies in Learning (iJET) 19, no. 06 (2024): 38–51. http://dx.doi.org/10.3991/ijet.v19i06.49829.

Full text

Abstract:

This study explores the integration of generative artificial intelligence (AI) with Exercise Generation Algorithm+ (EGAL+), a multi-objective harmony search (HS) metaheuristic-based algorithm capable of composing high-quality exercises. These exercises are characterized by their diversity, consistent difficulty, and comprehensive coverage of the source material, tailored to user preferences. One of the main challenges of using metaheuristics to compile exercises efficiently is the initial creation of a large question bank, which often demands significant time and effort from instructors. To overcome this challenge, the integration of a readily available existing generative AI module is proposed. This module is accessed through its application programming interface, autonomously populating the question bank. This sets the stage for EGAL+ to fine-tune the selection and assembly of specific exams. The resulting program enables educators to create an extensive question bank from any educational material, independent of the subject, and subsequently compose exercises with minimal effort. This approach leverages the synergistic benefits of both generative AI and metaheuristicbased optimization, offering a robust and efficient solution for exercise generation.

APA, Harvard, Vancouver, ISO, and other styles

35

Maarouf, Ibrahim ElSayed, and Sherif Usama Zeid. "PARAMETRIC APPROACH FOR GENERATING NEW MUQARNAS." Journal of Islamic Architecture 5, no. 3 (2019): 111–18. http://dx.doi.org/10.18860/jia.v5i3.5322.

Full text

Abstract:

In recent decades, the search for new geometrical innovations has been of great interest for contemporary architects artists, trying to escape the repetitive use of historical ornamental details of architectural styles orders or the absence of such ornaments in the modern style. This paper aims to lay down the basis for generating new muqarnas elements based on the cosmological nature of Islamic Architecture, but still preserving its concepts. The muqarnas was chosen because it is one of most original inventions of Islamic architecture and one of its most effective and widespread applications. Innovation in its design requires freedom of expression that can be limited by design software. Furthermore, the process of testing ideas can be tedious and time-consuming. Parametric and generative design, using Grasshopper, is used to reformulate the muqarnas generation process using visual programming. Parametric design and hypothetical geometric patterns in a linear or polar arraying direction produce a clearly defined muqarnas.

APA, Harvard, Vancouver, ISO, and other styles

36

Nasimov, Rashid, Nigorakhon Nasimova, Sanjar Mirzakhalilov, et al. "GAN-Based Novel Approach for Generating Synthetic Medical Tabular Data." Bioengineering 11, no. 12 (2024): 1288. https://doi.org/10.3390/bioengineering11121288.

Full text

Abstract:

The generation of synthetic medical data has become a focal point for researchers, driven by the increasing demand for privacy-preserving solutions. While existing generative methods heavily rely on real datasets for training, access to such data is often restricted. In contrast, statistical information about these datasets is more readily available, yet current methods struggle to generate tabular data solely from statistical inputs. This study addresses the gaps by introducing a novel approach that converts statistical data into tabular datasets using a modified Generative Adversarial Network (GAN) architecture. A custom loss function was incorporated into the training process to enhance the quality of the generated data. The proposed method is evaluated using fidelity and utility metrics, achieving “Good” similarity and “Excellent” utility scores. While the generated data may not fully replace real databases, it demonstrates satisfactory performance for training machine-learning algorithms. This work provides a promising solution for synthetic data generation when real datasets are inaccessible, with potential applications in medical data privacy and beyond.

APA, Harvard, Vancouver, ISO, and other styles

37

Liu, Yufeng, Yangchen Zhou, Fan Yang, Song Li, and Jun Wu. "An improved generative design approach based on graph grammar for pattern drawing." Machine Graphics and Vision 33, no. 1 (2024): 3–20. http://dx.doi.org/10.22630/mgv.2024.33.1.1.

Full text

Abstract:

Generative design is used to efficiently generate design solutions with powerful computational methods. Generative design based on shape grammar is currently the most commonly used approach, but it is difficult for shape grammar to formally analyze the generated pattern. Graph grammar derived from one-dimensional character grammar is mainly used for generating and analyzing abstract models of visual languages. However, there is a significant gap between the generated node-edge graphs and the representation of shape appearance. To address these problems, we propose an improved generative design approach based on virtual-node based continuous Coordinate Graph Grammar (vcCGG). This approach defines a new type of grammatical rule named node transformation rules to convert nodes into shapes with node transformation applications. By combining node transformation applications and L-applications in vcCGG, we can generate a node-edge graph as the structure of the pattern through L-applications, and then draw the shape outline, next adjust the positions of these shapes, thus relating abstract structures and the physical layouts of visual languages. At the end of the paper, we provide an example application of this approach: generating an illustration from Emma Talbot using a combination of node transformation applications and L-applications.

APA, Harvard, Vancouver, ISO, and other styles

38

Li, Haibing, and Roland Lachmayer. "Generative Design Approach for Modeling Creative Designs." IOP Conference Series: Materials Science and Engineering 408 (October 1, 2018): 012035. http://dx.doi.org/10.1088/1757-899x/408/1/012035.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Shi, Weili. "A Generative Approach to Chinese Shanshui Painting." IEEE Computer Graphics and Applications 37, no. 1 (2017): 15–19. http://dx.doi.org/10.1109/mcg.2017.13.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Chen, Changlu, Chaoxi Niu, Xia Zhan, and Kun Zhan. "Generative approach to unsupervised deep local learning." Journal of Electronic Imaging 28, no. 04 (2019): 1. http://dx.doi.org/10.1117/1.jei.28.4.043005.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Desolneux, Agnès. "When the a contrario approach becomes generative." International Journal of Computer Vision 116, no. 1 (2015): 46–65. http://dx.doi.org/10.1007/s11263-015-0825-x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Liu, Hong, and Yan Li. "Generative design supported by evolutionary computing approach." International Journal of Computer Applications in Technology 30, no. 1/2 (2007): 69. http://dx.doi.org/10.1504/ijcat.2007.015698.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Raghavan, S. V., D. Vasukiammaiyar, and Günter Haring. "Hierarchical approach to building generative networkload models." Computer Networks and ISDN Systems 27, no. 7 (1995): 1193–206. http://dx.doi.org/10.1016/0169-7552(94)00012-i.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Hinkelmann, Knut, and Dimitris Karagiannis. "Context-sensitive office tasks a generative approach." Decision Support Systems 8, no. 3 (1992): 255–67. http://dx.doi.org/10.1016/0167-9236(92)90018-k.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Andreeva, Tatiana A., Nikolay Yu Bykov, Tatiana A. Kompan, Valentin I. Kulagin, Alexander Ya Lukin, and Viktoriya V. Vlasova. "Precision Calorimeter Model Development: Generative Design Approach." Processes 11, no. 1 (2023): 152. http://dx.doi.org/10.3390/pr11010152.

Full text

Abstract:

In a wide range of applications, heating or cooling systems provide not only temperature changes, but also small temperature gradients in a sample or industrial facility. Although a conventional proportional-integral-derivative (PID) controller usually solves the problem, it is not optimal because it does not use information about the main sources of change—the current power of the heater or cooler. The quality of control can be significantly improved by including a model of thermal processes in the control algorithm. Although the temperature distribution in the device can be calculated from a full-fledged 3D model based on partial differential equations, this approach has at least two drawbacks: the presence of many difficult-to-determine parameters and excessive complexity for control tasks. The development of a simplified mathematical model, free from these shortcomings, makes it possible to significantly improve the quality of control. The development of such a model using generative design techniques is considered as an example for a precision adiabatic calorimeter designed to measure the specific heat capacity of solids. The proposed approach, which preserves the physical meaning of the equations, allows for not only significantly improving the consistency between the calculation and experimental data, but also improving the understanding of real processes in the installation.

APA, Harvard, Vancouver, ISO, and other styles

46

Lee, Chei Sian, Li En Tan, and Dion Hoe-Lian Goh. "Examining generation Z's use of generative AI from an affordance-based approach." Information Research an international electronic journal 30, iConf (2025): 1095–102. https://doi.org/10.47989/ir30iconf47083.

Full text

Abstract:

Introduction. This paper uses the affordances framework to investigate how Generation Z (GenZ) students in higher education use generative AI (GenAI). There is an increasing need to gain a deeper understanding of GenZ’s interaction with artificial intelligence tools to better support their integration into higher education and the workforce. Method. Data was collated from semi-structured interviews with 34 GenZ students in higher education. Analysis. Thematic analysis was conducted on the qualitative data collected from the semi-structured interviews. Results. The findings suggest GenZ students have seamlessly integrated GenAI into diverse aspects of their lives. This study highlighted three main GenAI affordances that resonate with GenZ students: a) content searching and curation b) content generation and ideation, and c) content enhancement and refinement, revealing new opportunities for information access. Conclusions. This study shed light on the perceived affordances of GenAI for GenZs, addressing a gap in the current literature on GenAI. The findings underscore the significant extent to which GenAI has been integrated into GenZ students’ daily lives. Our study contributes to a better understanding of how GenAI’s affordances facilitate and support GenZ students, providing invaluable insights that can inform future policies on developing literacy for AI use tailored to this group.

APA, Harvard, Vancouver, ISO, and other styles

47

Yunqian, Zhang. "AI-DRIVEN BACKGROUND GENERATION FOR MANGA ILLUSTRATIONS: A DEEP GENERATIVE MODEL APPROACH." ORESTA 7, no. 1 (2024): 158–75. https://doi.org/10.5281/zenodo.15080622.

Full text

Abstract:

<em>This paper introduces the generation technique of manga illustration background, discusses the traditional background generation technique and stylized migration technique, and points out that the application of AI technology provides new possibilities for the creation of manga illustration backgrounds. Aiming at the limitations of traditional methods, the design concept and principle of conditional generative model based on deep learning are proposed, the implementation principles of convolutional neural network and generative adversarial network are introduced, and the conditional manga illustration background generation model based on deep learning is proposed by combining the two. The paper uses MindSpore software to train CNN models.CNN models are very good for processing data such as images and are able to reduce the number of parameters in the model and increase the speed of training the model.The model data has a wide range of applications and is capable of removing the influence of character factors from the image while providing high resolution.The model can effectively realize the conditional generation of manga illustration background. The practical effect of this technology is demonstrated through a case study and technical exploration of manga illustration background generation technology, which demonstrates the potential of the new technology and its application in creating richer and more vivid comic backgrounds. In the future, with the continuous improvement and promotion of this technology, more similar cases are expected to be seen, bringing more possibilities and innovations to the creation of comics and illustrations.</em>

APA, Harvard, Vancouver, ISO, and other styles

48

Wang, Xiaolong, Zhijian He, and Xiaojiang Peng. "Artificial-Intelligence-Generated Content with Diffusion Models: A Literature Review." Mathematics 12, no. 7 (2024): 977. http://dx.doi.org/10.3390/math12070977.

Full text

Abstract:

Diffusion models have swiftly taken the lead in generative modeling, establishing unprecedented standards for producing high-quality, varied outputs. Unlike Generative Adversarial Networks (GANs)—once considered the gold standard in this realm—diffusion models bring several unique benefits to the table. They are renowned for generating outputs that more accurately reflect the complexity of real-world data, showcase a wider array of diversity, and are based on a training approach that is comparatively more straightforward and stable. This survey aims to offer an exhaustive overview of both the theoretical underpinnings and practical achievements of diffusion models. We explore and outline three core approaches to diffusion modeling: denoising diffusion probabilistic models, score-based generative models, and stochastic differential equations. Subsequently, we delineate the algorithmic enhancements of diffusion models across several pivotal areas. A notable aspect of this review is an in-depth analysis of leading generative models, examining how diffusion models relate to and evolve from previous generative methodologies, offering critical insights into their synergy. A comparative analysis of the merits and limitations of different generative models is a vital component of our discussion. Moreover, we highlight the applications of diffusion models across computer vision, multi-modal generation, and beyond, culminating in significant conclusions and suggesting promising avenues for future investigation.

APA, Harvard, Vancouver, ISO, and other styles

49

Han, Jason, and Tirthak Patel. "Turning Quantum Noise on its Head: Using the Noise for Diffusion Models to Generate Images." ACM SIGMETRICS Performance Evaluation Review 52, no. 4 (2025): 23–24. https://doi.org/10.1145/3725536.3725548.

Full text

Abstract:

In this work, we propose positively using noise from quantum computers, which is currently viewed as a hindrance for performing useful computation, instead of simulated noise to train generative image diffusion models, which have two primary advantages: True Noise Generation. A key quality of random quantum fluctuations is that they are independent of human input. Current means of generating noise in diffusion models are pseudo-random, meaning that randomness is simulated using human-defined algorithms. Parallel Noise Generation. In quantum computers, each quantum bit (or qubit) has random fluctuations, so we can use multiple quantum bits to generate randomness in parallel. To parallelize noise generation classically, we would need to use more resources, which is not needed in quantum computers. Our approach, Quantum Image Noise-based Generative Diffusion Models (referred to as QINGDM), utilizes these benefits of quantum noise.

APA, Harvard, Vancouver, ISO, and other styles

50

Soddu, Celestino. "New Naturality: A Generative Approach to Art and Design." Leonardo 35, no. 3 (2002): 291–94. http://dx.doi.org/10.1162/002409402760105299.

Full text

Abstract:

In the field of generative art and design, design concepts are represented as code. This generative code functions as DNA does in nature. It uses artificial life to generate a multiplicity of possible artworks, artificial events, architectures and virtual environments. In the generative approach the real artwork is not merely a product, such as an image or 3D model. The generative artwork is an Idea-Product. It represents an artificial species able to generate an endless sequence of individual events, each one different, unique and unrepeatable but belonging to the same identifiable design Idea. The author's project, Argenia, realizes the “new naturality” of artificial objects.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Generative approach'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles