Artigos de revistas: "Neuro-Symbolic Artificial intelligence"

1

Marra, Giuseppe. "From Statistical Relational to Neuro-Symbolic Artificial Intelligence." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 20 (2024): 22678. http://dx.doi.org/10.1609/aaai.v38i20.30294.

Texto completo da fonte

Resumo:

The integration of learning and reasoning is one of the key challenges in artificial intelligence and machine learning today. The area of Neuro-Symbolic AI (NeSy) tackles this challenge by integrating symbolic reasoning with neural networks. In our recent work, we provided an introduction to NeSy by drawing several parallels to another field that has a rich tradition in integrating learning and reasoning, namely Statistical Relational Artificial Intelligence (StarAI).

Estilos ABNT, Harvard, Vancouver, APA, etc.

2

Morel, Gilles. "Neuro-symbolic A.I. for the smart city." Journal of Physics: Conference Series 2042, no. 1 (2021): 012018. http://dx.doi.org/10.1088/1742-6596/2042/1/012018.

Texto completo da fonte

Resumo:

Abstract Smart building and smart city specialists agree that complex, innovative use cases, especially those using cross-domain and multi-source data, need to make use of Artificial Intelligence (AI). However, today’s AI mainly concerns machine learning and artificial neural networks (deep learning), whereas the first forty years of the discipline (the last decades of the 20th century) were essentially focused on a knowledge-based approach, which is still relevant today for some tasks. In this article we advocate a merging of these two AI trends – an approach known as neuro-symbolic AI – for the smart city, and point the way towards a complete integration of the two technologies, compatible with standard software.

Estilos ABNT, Harvard, Vancouver, APA, etc.

3

van Bekkum, Michael, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, and Annette ten Teije. "Modular design patterns for hybrid learning and reasoning systems." Applied Intelligence 51, no. 9 (2021): 6528–46. http://dx.doi.org/10.1007/s10489-021-02394-3.

Texto completo da fonte

Resumo:

AbstractThe unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognized as one of the key challenges of modern AI. Recent years have seen a large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse, mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper, we analyze a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems organized in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognized until now. Finally, our design patterns extend and refine Kautz’s earlier attempt at categorizing neuro-symbolic architectures.

Estilos ABNT, Harvard, Vancouver, APA, etc.

4

Ebrahimi, Monireh, Aaron Eberhart, Federico Bianchi, and Pascal Hitzler. "Towards bridging the neuro-symbolic gap: deep deductive reasoners." Applied Intelligence 51, no. 9 (2021): 6326–48. http://dx.doi.org/10.1007/s10489-020-02165-6.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

5

Barbosa, Raul, Douglas O. Cardoso, Diego Carvalho, and Felipe M. G. França. "Weightless neuro-symbolic GPS trajectory classification." Neurocomputing 298 (July 2018): 100–108. http://dx.doi.org/10.1016/j.neucom.2017.11.075.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

6

Bahamid, Alala, Azhar Mohd Ibrahim, and Amir Akramin Shafie. "Crowd evacuation with human-level intelligence via neuro-symbolic approach." Advanced Engineering Informatics 60 (April 2024): 102356. http://dx.doi.org/10.1016/j.aei.2024.102356.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

7

Škrlj, Blaž, Matej Martinc, Nada Lavrač, and Senja Pollak. "autoBOT: evolving neuro-symbolic representations for explainable low resource text classification." Machine Learning 110, no. 5 (2021): 989–1028. http://dx.doi.org/10.1007/s10994-021-05968-x.

Texto completo da fonte

Resumo:

AbstractLearning from texts has been widely adopted throughout industry and science. While state-of-the-art neural language models have shown very promising results for text classification, they are expensive to (pre-)train, require large amounts of data and tuning of hundreds of millions or more parameters. This paper explores how automatically evolved text representations can serve as a basis for explainable, low-resource branch of models with competitive performance that are subject to automated hyperparameter tuning. We present autoBOT (automatic Bags-Of-Tokens), an autoML approach suitable for low resource learning scenarios, where both the hardware and the amount of data required for training are limited. The proposed approach consists of an evolutionary algorithm that jointly optimizes various sparse representations of a given text (including word, subword, POS tag, keyword-based, knowledge graph-based and relational features) and two types of document embeddings (non-sparse representations). The key idea of autoBOT is that, instead of evolving at the learner level, evolution is conducted at the representation level. The proposed method offers competitive classification performance on fourteen real-world classification tasks when compared against a competitive autoML approach that evolves ensemble models, as well as state-of-the-art neural language models such as BERT and RoBERTa. Moreover, the approach is explainable, as the importance of the parts of the input space is part of the final solution yielded by the proposed optimization procedure, offering potential for meta-transfer learning.

Estilos ABNT, Harvard, Vancouver, APA, etc.

8

Prentzas, Jim, and Ioannis Hatzilygeroudis. "Neurules and connectionist expert systems: Unexplored neuro-symbolic reasoning aspects." Intelligent Decision Technologies 15, no. 4 (2022): 761–77. http://dx.doi.org/10.3233/idt-210211.

Texto completo da fonte

Resumo:

Neuro-symbolic approaches combine neural and symbolic methods. This paper explores aspects regarding the reasoning mechanisms of two neuro-symbolic approaches, that is, neurules and connectionist expert systems. Both provide reasoning and explanation facilities. Neurules are a type of neuro-symbolic rules tightly integrating the neural and symbolic components, giving pre-eminence to the symbolic component. Connectionist expert systems give pre-eminence to the connectionist component. This paper explores reasoning aspects about neurules and connectionist expert systems that have not been previously addressed. As far as neurules are concerned, an aspect playing a role in conflict resolution (i.e., order of neurules) is explored. Experimental results show an improvement in reasoning efficiency. As far as connectionist expert systems are concerned, variations of the reasoning mechanism are explored. Experimental results are presented for them as well showing that one of the variations generally performs better than the others.

Estilos ABNT, Harvard, Vancouver, APA, etc.

9

Shilov, Nikolay, Andrew Ponomarev, and Alexander Smirnov. "The Analysis of Ontology-Based Neuro-Symbolic Intelligence Methods for Collaborative Decision Support." Informatics and Automation 22, no. 3 (2023): 576–615. http://dx.doi.org/10.15622/ia.22.3.4.

Texto completo da fonte

Resumo:

The neural network approach to AI, which has become especially widespread in the last decade, has two significant limitations – training of a neural network, as a rule, requires a very large number of samples (not always available), and the resulting models often are not well interpretable, which can reduce their credibility. The use of symbols as the basis of collaborative processes, on the one hand, and the proliferation of neural network AI, on the other hand, necessitate the synthesis of neural network and symbolic paradigms in relation to the creation of collaborative decision support systems. The article presents the results of an analytical review in the field of ontology-oriented neuro-symbolic artificial intelligence with an emphasis on solving problems of knowledge exchange during collaborative decision support. Specifically, the review attempts to answer two questions: 1. how symbolic knowledge, represented as an ontology, can be used to improve AI agents operating on the basis of neural networks (knowledge transfer from a person to AI agents); 2. how symbolic knowledge, represented as an ontology, can be used to interpret decisions made by AI agents and explain these decisions (transfer of knowledge from an AI agent to a person). As a result of the review, recommendations were formulated on the choice of methods for introducing symbolic knowledge into neural network models, and promising areas of ontology-oriented methods for explaining neural networks were identified.

Estilos ABNT, Harvard, Vancouver, APA, etc.

10

Kishor, Rabinandan. "Neuro-Symbolic AI: Bringing a new era of Machine Learning." International Journal of Research Publication and Reviews 03, no. 12 (2022): 2326–36. http://dx.doi.org/10.55248/gengpi.2022.31271.

Texto completo da fonte

Resumo:

Processing Natural Language using machines is not a new concept. Back in 1940 researchers estimated the importance of a machine that could translate one language to another. Further, during 1957-1970 researchers split into two divisions concerning NLP: symbolic and stochastic. This paper presents an extensive review of recent breakthroughs in Neuro Symbolic Artificial Intelligence (NSAI), an area of AI research which seeks to combine traditional rules-based AI approaches with modern deep learning techniques. Neuro Symbolic models have already demonstrated the capability to outperform state-of-the-art deep learning models in domains such as image and video reasoning. Such models not only performed better when trained on a fraction of dataset compared with traditional machine learning models, but also solved an underlined issue called generalization of deep neural network systems. We also find that symbolic models are good in visual question answering (VQA). In this paper, we also review research results related to Neuro Symbolic AI with the objective of exploring the importance of such AI systems and how it would shape the future of AI as a whole. We discuss different types of dataset of Visual Question Answering (VQA) tasks based on NSAI and extensive comparison of performance of different NSAI models. Later, the article focuses on the contemporary real time application of NSAI systems and how NSAI is shaping the world’s different sectors including finance, healthcare, and cyber security.

Estilos ABNT, Harvard, Vancouver, APA, etc.

11

Smirnov, A. V., A. V. Ponomarev, N. G. Shilov, and T. V. Levashova. "Collaborative Decision Support Systems Based on Neuro-Symbolic Artificial Intelligence: Problems and Generalized Conceptual Model." Scientific and Technical Information Processing 50, no. 6 (2023): 635–45. http://dx.doi.org/10.3103/s0147688223060151.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

12

Skryagin, Arseny, Daniel Ochs, Devendra Singh Dhami, and Kristian Kersting. "Scalable Neural-Probabilistic Answer Set Programming." Journal of Artificial Intelligence Research 78 (November 16, 2023): 579–617. http://dx.doi.org/10.1613/jair.1.15027.

Texto completo da fonte

Resumo:

The goal of combining the robustness of neural networks and the expressiveness of symbolic methods has rekindled the interest in Neuro-Symbolic AI. Deep Probabilistic Programming Languages (DPPLs) have been developed for probabilistic logic programming to be carried out via the probability estimations of deep neural networks (DNNs). However, recent SOTA DPPL approaches allow only for limited conditional probabilistic queries and do not offer the power of true joint probability estimation. In our work, we propose an easy integration of tractable probabilistic inference within a DPPL. To this end, we introduce SLASH, a novel DPPL that consists of Neural-Probabilistic Predicates (NPPs) and a logic program, united via answer set programming (ASP). NPPs are a novel design principle allowing for combining all deep model types and combinations thereof to be represented as a single probabilistic predicate. In this context, we introduce a novel +/− notation for answering various types of probabilistic queries by adjusting the atom notations of a predicate. To scale well, we show how to prune the stochastically insignificant parts of the (ground) program, speeding up reasoning without sacrificing the predictive performance. We evaluate SLASH on various tasks, including the benchmark task of MNIST addition and Visual Question Answering (VQA).

Estilos ABNT, Harvard, Vancouver, APA, etc.

13

Souici-Meslati, Labiba, and Mokhtar Sellami. "A Hybrid Neuro-Symbolic Approach for Arabic Handwritten Word Recognition." Journal of Advanced Computational Intelligence and Intelligent Informatics 10, no. 1 (2006): 17–25. http://dx.doi.org/10.20965/jaciii.2006.p0017.

Texto completo da fonte

Resumo:

In this article, we suggest a system that automatically constructs knowledge based artificial neural networks (KBANN) for the holistic recognition of handwritten Arabic words in limited lexicons. To build a neuro-symbolic KBANN classifier for a given vocabulary, ideal samples of its words are first submitted to a structural feature extraction module. The analysis of the presence and possible occurrence numbers for these features in the considered lexicon enables to generate a symbolic knowledge base reflecting a hierarchical classification of the words. A rules-to-network translation algorithm uses this knowledge to build a multilayer neural network. It determines precisely its architecture and initializes its connections with specific values rather than random values, as is the case in classical neural networks. This construction approach provides the network with theoretical knowledge and reduces the training stage, which remains necessary because of styles and writing conditions variability. After this empirical training stage using real examples, the network acquires a final topology, which allows it to recognize new handwritten words. The proposed method has been tested on the automated construction of neuro-symbolic classifiers for two Arabic lexicons: literal amounts and city names. The application of this approach to the recognition of handwritten words or characters in different scripts and languages is also considered.

Estilos ABNT, Harvard, Vancouver, APA, etc.

14

Onchis, Darian, Codruta Istin, and Eduard Hogea. "A Neuro-Symbolic Classifier with Optimized Satisfiability for Monitoring Security Alerts in Network Traffic." Applied Sciences 12, no. 22 (2022): 11502. http://dx.doi.org/10.3390/app122211502.

Texto completo da fonte

Resumo:

We introduce in this paper a neuro-symbolic predictive model based on Logic Tensor Networks, capable of discriminating and at the same time of explaining the bad connections, called alerts or attacks, and the normal connections. The proposed classifier incorporates both the ability of deep neural networks to improve on their own through learning from experience and the interpretability of the results provided by the symbolic artificial intelligence approach. Compared to other existing solutions, we advance in the discovery of potential security breaches from a cognitive perspective. By introducing the reasoning in the model, our aim is to further reduce the human staff needed to deal with the cyber-threat hunting problem. To justify the need for shifting towards hybrid systems for this task, the design, the implementation, and the comparison of the dense neural network and the neuro-symbolic model is performed in detail. While in terms of standard accuracy, both models demonstrated similar precision, we further introduced for our model the concept of interactive accuracy as a way of querying the model results at any time coupled with deductive reasoning over data. By applying our model on the CIC-IDS2017 dataset, we reached an accuracy of 0.95, with levels of satisfiability around 0.85. Other advantages such as overfitting mitigation and scalability issues are also presented.

Estilos ABNT, Harvard, Vancouver, APA, etc.

15

Papadimitriou, Stergios, and Constantinos Terzidis. "Symbolic adaptive neuro-fuzzy inference for data mining of heterogenous data." Intelligent Data Analysis 7, no. 4 (2003): 327–46. http://dx.doi.org/10.3233/ida-2003-7405.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

16

Feng, Yufei, Xiaoyu Yang, Xiaodan Zhu, and Michael Greenspan. "Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference." Transactions of the Association for Computational Linguistics 10 (2022): 240–56. http://dx.doi.org/10.1162/tacl_a_00458.

Texto completo da fonte

Resumo:

Abstract We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision. The model samples and rewards specific reasoning paths through policy gradient, in which the introspective revision algorithm modifies intermediate symbolic reasoning steps to discover reward-earning operations as well as leverages external knowledge to alleviate spurious reasoning and training inefficiency. The framework is supported by properly designed local relation models to avoid input entangling, which helps ensure the interpretability of the proof paths. The proposed model has built-in interpretability and shows superior capability in monotonicity inference, systematic generalization, and interpretability, compared with previous models on the existing datasets.

Estilos ABNT, Harvard, Vancouver, APA, etc.

17

Yuan, Ye, Bo Tang, Tianfei Zhou, Zhiwei Zhang, and Jianbin Qin. "nsDB: Architecting the Next Generation Database by Integrating Neural and Symbolic Systems." Proceedings of the VLDB Endowment 17, no. 11 (2024): 3283–89. http://dx.doi.org/10.14778/3681954.3682000.

Texto completo da fonte

Resumo:

In this paper, we propose nsDB, a novel neuro-symbolic database system that integrates neural and symbolic system architectures natively to address the weaknesses of each, providing a strong database capable of data managing, model learning, and complex analytical query processing over multi-modal data. We employ a real-world NBA data analytical query as an example to illustrate the functionality of each component in nsDB and highlight the research challenges to build it. We then present the key design principles and our preliminary attempts to address them. In a nutshell, we envision that the next generation database system nsDB integrates the complex neural system with the simple symbolic system. Undoubtedly, nsDB will serve as a bridge between databases with AI models, which abstracts away the AI complexities but allows end users to enjoy the strong capabilities of them. We are in the early stages of the journey to build nsDB, there are many opening challenges, e.g., in-database model training, multi-objective query optimization, and database agent development. We hope the researchers from different communities (e.g., system, architecture, database, artificial intelligence) could tackle them together.

Estilos ABNT, Harvard, Vancouver, APA, etc.

18

Pallagani, Vishal, Bharath Chandra Muppasani, Kaushik Roy, et al. "On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)." Proceedings of the International Conference on Automated Planning and Scheduling 34 (May 30, 2024): 432–44. http://dx.doi.org/10.1609/icaps.v34i1.31503.

Texto completo da fonte

Resumo:

Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity. Based on a comprehensive review of 126 papers, this paper investigates eight categories based on the unique applications of LLMs in addressing various aspects of planning problems: language translation, plan generation, model construction, multi-agent planning, interactive planning, heuristics optimization, tool integration, and brain-inspired planning. For each category, we articulate the issues considered and existing gaps. A critical insight resulting from our review is that the true potential of LLMs unfolds when they are integrated with traditional symbolic planners, pointing towards a promising neuro-symbolic approach. This approach effectively combines the generative aspects of LLMs with the precision of classical planning methods. By synthesizing insights from existing literature, we underline the potential of this integration to address complex planning challenges. Our goal is to encourage the ICAPS community to recognize the complementary strengths of LLMs and symbolic planners, advocating for a direction in automated planning that leverages these synergistic capabilities to develop more advanced and intelligent planning systems. We aim to keep the categorization of papers updated on https://ai4society.github.io/LLM-Planning-Viz/, a collaborative resource that allows researchers to contribute and add new literature to the categorization.

Estilos ABNT, Harvard, Vancouver, APA, etc.

19

Palconit, Maria Gemel B., Ronnie S. Concepcion II, Jonnel D. Alejandrino, et al. "Three-Dimensional Stereo Vision Tracking of Multiple Free-Swimming Fish for Low Frame Rate Video." Journal of Advanced Computational Intelligence and Intelligent Informatics 25, no. 5 (2021): 639–46. http://dx.doi.org/10.20965/jaciii.2021.p0639.

Texto completo da fonte

Resumo:

Three-dimensional multiple fish tracking has gained significant research interest in quantifying fish behavior. However, most tracking techniques use a high frame rate, which is currently not viable for real-time tracking applications. This study discusses multiple fish-tracking techniques using low-frame-rate sampling of stereo video clips. The fish were tagged and tracked based on the absolute error of the predicted indices using past and present fish centroid locations and a deterministic frame index. In the predictor sub-system, linear regression and machine learning algorithms intended for nonlinear systems, such as the adaptive neuro-fuzzy inference system (ANFIS), symbolic regression, and Gaussian process regression (GPR), were investigated. The results showed that, in the context of tagging and tracking accuracy, the symbolic regression attained the best performance, followed by the GPR, that is, 74% to 100% and 81% to 91%, respectively. Considering the computation time, symbolic regression resulted in the highest computing lag of approximately 946 ms per iteration, whereas GPR achieved the lowest computing time of 39 ms.

Estilos ABNT, Harvard, Vancouver, APA, etc.

20

Hua, Hua, Dongxu Li, Ruiqi Li, Peng Zhang, Jochen Renz, and Anthony Cohn. "Towards Explainable Action Recognition by Salient Qualitative Spatial Object Relation Chains." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 5 (2022): 5710–18. http://dx.doi.org/10.1609/aaai.v36i5.20513.

Texto completo da fonte

Resumo:

In order to be trusted by humans, Artificial Intelligence agents should be able to describe rationales behind their decisions. One such application is human action recognition in critical or sensitive scenarios, where trustworthy and explainable action recognizers are expected. For example, reliable pedestrian action recognition is essential for self-driving cars and explanations for real-time decision making are critical for investigations if an accident happens. In this regard, learning-based approaches, despite their popularity and accuracy, are disadvantageous due to their limited interpretability. This paper presents a novel neuro-symbolic approach that recognizes actions from videos with human-understandable explanations. Specifically, we first propose to represent videos symbolically by qualitative spatial relations between objects called qualitative spatial object relation chains. We further develop a neural saliency estimator to capture the correlation between such object relation chains and the occurrence of actions. Given an unseen video, this neural saliency estimator is able to tell which object relation chains are more important for the action recognized. We evaluate our approach on two real-life video datasets, with respect to recognition accuracy and the quality of generated action explanations. Experiments show that our approach achieves superior performance on both aspects to previous symbolic approaches, thus facilitating trustworthy intelligent decision making. Our approach can be used to augment state-of-the-art learning approaches with explainabilities.

Estilos ABNT, Harvard, Vancouver, APA, etc.

21

Prentzas, Jim, and Ioannis Hatzilygeroudis. "Assessment of life insurance applications: an approach integrating neuro-symbolic rule-based with case-based reasoning." Expert Systems 33, no. 2 (2015): 145–60. http://dx.doi.org/10.1111/exsy.12137.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

22

Hu, Yiwen, and Markus J. Buehler. "Deep language models for interpretative and predictive materials science." APL Machine Learning 1, no. 1 (2023): 010901. http://dx.doi.org/10.1063/5.0134317.

Texto completo da fonte

Resumo:

Machine learning (ML) has emerged as an indispensable methodology to describe, discover, and predict complex physical phenomena that efficiently help us learn underlying functional rules, especially in cases when conventional modeling approaches cannot be applied. While conventional feedforward neural networks are typically limited to performing tasks related to static patterns in data, recursive models can both work iteratively based on a changing input and discover complex dynamical relationships in the data. Deep language models can model flexible modalities of data and are capable of learning rich dynamical behaviors as they operate on discrete or continuous symbols that define the states of a physical system, yielding great potential toward end-to-end predictions. Similar to how words form a sentence, materials can be considered as a self-assembly of physically interacted building blocks, where the emerging functions of materials are analogous to the meaning of sentences. While discovering the fundamental relationships between building blocks and function emergence can be challenging, language models, such as recurrent neural networks and long-short term memory networks, and, in particular, attention models, such as the transformer architecture, can solve many such complex problems. Application areas of such models include protein folding, molecular property prediction, prediction of material failure of complex nonlinear architected materials, and also generative strategies for materials discovery. We outline challenges and opportunities, especially focusing on extending the deep-rooted kinship of humans with symbolism toward generalizable artificial intelligence (AI) systems using neuro-symbolic AI, and outline how tools such as ChatGPT and DALL·E can drive materials discovery.

Estilos ABNT, Harvard, Vancouver, APA, etc.

23

Sarker, Md Kamruzzaman, Lu Zhou, Aaron Eberhart, and Pascal Hitzler. "Neuro-symbolic artificial intelligence." AI Communications, September 16, 2021, 1–13. http://dx.doi.org/10.3233/aic-210084.

Texto completo da fonte

Resumo:

Neuro-Symbolic Artificial Intelligence – the combination of symbolic methods with methods that are based on artificial neural networks – has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.

Estilos ABNT, Harvard, Vancouver, APA, etc.

24

Hitzler, Pascal, Aaron Eberhart, Monireh Ebrahimi, Md Kamruzzaman Sarker, and Lu Zhou. "Neuro-Symbolic Approaches in Artificial Intelligence." National Science Review, March 4, 2022. http://dx.doi.org/10.1093/nsr/nwac035.

Texto completo da fonte

Resumo:

Abstract Neuro-Symbolic Artificial Intelligence refers to a field of research and applications that combines machine learning methods based on artificial neural networks, such as deep learning, with symbolic approaches to computing and Artificial Intelligence (AI), as can be found for example in the AI subfield of Knowledge Representation and Reasoning. Neuro-Symbolic AI has a long history, however it remained a rather niche topic until recently, when landmark advances in machine learning – prompted by deep learning – caused a significant rise in interest and research activity in combining neural and symbolic methods. In this overview, we provide a rough guide to key research directions, and literature pointers for anybody interested in learning more about the field.

Estilos ABNT, Harvard, Vancouver, APA, etc.

25

Bhuyan, Bikram Pratim, Amar Ramdane-Cherif, Ravi Tomar, and T. P. Singh. "Neuro-symbolic artificial intelligence: a survey." Neural Computing and Applications, June 6, 2024. http://dx.doi.org/10.1007/s00521-024-09960-z.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

26

Lu, Zhen, Imran Afridi, Hong Jin Kang, Ivan Ruchkin, and Xi Zheng. "Surveying neuro-symbolic approaches for reliable artificial intelligence of things." Journal of Reliable Intelligent Environments, July 26, 2024. http://dx.doi.org/10.1007/s40860-024-00231-1.

Texto completo da fonte

Resumo:

AbstractThe integration of Artificial Intelligence (AI) with the Internet of Things (IoT), known as the Artificial Intelligence of Things (AIoT), enhances the devices’ processing and analysis capabilities and disrupts such sectors as healthcare, industry, and oil. However, AIoT’s complexity and scale are challenging for traditional machine learning (ML). Deep learning offers a solution but has limited testability, verifiability, and interpretability. In turn, the neuro-symbolic paradigm addresses these challenges by combining the robustness of symbolic AI with the flexibility of DL, enabling AI systems to reason, make decisions, and generalize knowledge from large datasets better. This paper reviews state-of-the-art DL models for IoT, identifies their limitations, and explores how neuro-symbolic methods can overcome them. It also discusses key challenges and research opportunities in enhancing AIoT reliability with neuro-symbolic approaches, including hard-coded symbolic AI, multimodal sensor data, biased interpretability, trading-off interpretability, and performance, complexity in integrating neural networks and symbolic AI, and ethical and societal challenges.

Estilos ABNT, Harvard, Vancouver, APA, etc.

27

Bueff, Andreas, and Vaishak Belle. "Learning explanatory logical rules in non-linear domains: a neuro-symbolic approach." Machine Learning, April 8, 2024. http://dx.doi.org/10.1007/s10994-024-06538-7.

Texto completo da fonte

Resumo:

AbstractDeep neural networks, despite their capabilities, are constrained by the need for large-scale training data, and often fall short in generalisation and interpretability. Inductive logic programming (ILP) presents an intriguing solution with its data-efficient learning of first-order logic rules. However, ILP grapples with challenges, notably the handling of non-linearity in continuous domains. With the ascent of neuro-symbolic ILP, there’s a drive to mitigate these challenges, synergising deep learning with relational ILP models to enhance interpretability and create logical decision boundaries. In this research, we introduce a neuro-symbolic ILP framework, grounded on differentiable Neural Logic networks, tailored for non-linear rule extraction in mixed discrete-continuous spaces. Our methodology consists of a neuro-symbolic approach, emphasising the extraction of non-linear functions from mixed domain data. Our preliminary findings showcase our architecture’s capability to identify non-linear functions from continuous data, offering a new perspective in neural-symbolic research and underlining the adaptability of ILP-based frameworks for regression challenges in continuous scenarios.

Estilos ABNT, Harvard, Vancouver, APA, etc.

28

Shi, Tuo, Hui Zhang, Shiyu Cui, et al. "Stochastic neuro-fuzzy system implemented in memristor crossbar arrays." Science Advances 10, no. 12 (2024). http://dx.doi.org/10.1126/sciadv.adl3135.

Texto completo da fonte

Resumo:

Neuro-symbolic artificial intelligence has garnered considerable attention amid increasing industry demands for high-performance neural networks that are interpretable and adaptable to previously unknown problem domains with minimal reconfiguration. However, implementing neuro-symbolic hardware is challenging due to the complexity in symbolic knowledge representation and calculation. We experimentally demonstrated a memristor-based neuro-fuzzy hardware based on TiN/TaO x /HfO x /TiN chips that is superior to its silicon-based counterpart in terms of throughput and energy efficiency by using array topological structure for knowledge representation and physical laws for computing. Intrinsic memristor variability is fully exploited to increase robustness in knowledge representation. A hybrid in situ training strategy is proposed for error minimizing in training. The hardware adapts easier to a previously unknown environment, achieving ~6.6 times faster convergence and ~6 times lower error than deep learning. The hardware energy efficiency is over two orders of magnitude greater than field-programmable gate arrays. This research greatly extends the capability of memristor-based neuromorphic computing systems in artificial intelligence.

Estilos ABNT, Harvard, Vancouver, APA, etc.

29

Huang, Zhen. "Introducing Neuro-Symbolic Artificial Intelligence to Humanities and Social Sciences: Why Is It Possible and What Can Be Done?" TEM Journal, November 25, 2022, 1863–70. http://dx.doi.org/10.18421/tem114-54.

Texto completo da fonte

Resumo:

With the support of artificial intelligence (AI), the smart applications in all walks of life have brought great changes to human society. Not only being concerned, analysed and criticized by scholars from Humanities and social sciences, AI also plays an important role in empirical research methods, thus facilitating the transformation of research paradigms in these fields. At present, neuro-symbolic AI, as a new product of the integration of two major factions in the field of artificial intelligence - connectionism and symbolism, has high application value in studying and solving the humanistic and social problems involving massive data due to its learning capability of perceiving the environment as well as reasoning capability of manipulating symbols. The introduction of neuro-symbolic AI is also of great significance for the development of emerging interdisciplinary fields such as digital humanities and computational social sciences. This paper aims to clarify the connections between neuro-symbolic AI and Humanities and social sciences, summarize the latest developing trends and representative applications, and explore a feasible path for the expansion of pluralistic methodologies in Humanities and social sciences to adapt to the age of big data.

Estilos ABNT, Harvard, Vancouver, APA, etc.

30

He, Hao-Yuan, Wang-Zhou Dai, and Ming Li. "Reduced implication-bias logic loss for neuro-symbolic learning." Machine Learning, January 30, 2024. http://dx.doi.org/10.1007/s10994-023-06436-4.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

31

Mitchener, Ludovico, David Tuckey, Matthew Crosby, and Alessandra Russo. "Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework." Machine Learning, April 7, 2022. http://dx.doi.org/10.1007/s10994-022-06142-7.

Texto completo da fonte

Resumo:

AbstractIn this paper we introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement learning framework. The Detect component is composed of a traditional computer vision object detector and tracker. The Act component houses a set of options, high-level actions enacted by pre-trained deep reinforcement learning (DRL) policies. The Understand component provides a novel answer set programming (ASP) paradigm for symbolically implementing a meta-policy over options and effectively learning it using inductive logic programming (ILP). We evaluate our framework on the Animal-AI (AAI) competition testbed, a set of physical cognitive reasoning problems. Given a set of pre-trained DRL policies, DUA requires only a few examples to learn a meta-policy that allows it to improve the state-of-the-art on multiple of the most challenging categories from the testbed. DUA constitutes the first holistic hybrid integration of computer vision, ILP and DRL applied to an AAI-like environment and sets the foundations for further use of ILP in complex DRL challenges.

Estilos ABNT, Harvard, Vancouver, APA, etc.

32

Munir, Md Shirajum, Ki Tae Kim, Apurba Adhikary, et al. "Neuro-Symbolic Explainable Artificial Intelligence Twin for Zero-Touch IoE in Wireless Network." IEEE Internet of Things Journal, 2023, 1. http://dx.doi.org/10.1109/jiot.2023.3303713.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

33

Derkinderen, Vincent, Robin Manhaeve, Pedro Zuidberg Dos Martires, and Luc De Raedt. "Semirings for probabilistic and neuro-symbolic logic programming." International Journal of Approximate Reasoning, January 2024, 109130. http://dx.doi.org/10.1016/j.ijar.2024.109130.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

34

BARBARA, VITO, MASSIMO GUARASCIO, NICOLA LEONE, et al. "Neuro-Symbolic AI for Compliance Checking of Electrical Control Panels." Theory and Practice of Logic Programming, July 10, 2023, 1–17. http://dx.doi.org/10.1017/s1471068423000170.

Texto completo da fonte

Resumo:

Abstract Artificial Intelligence plays a main role in supporting and improving smart manufacturing and Industry 4.0, by enabling the automation of different types of tasks manually performed by domain experts. In particular, assessing the compliance of a product with the relative schematic is a time-consuming and prone-to-error process. In this paper, we address this problem in a specific industrial scenario. In particular, we define a Neuro-Symbolic approach for automating the compliance verification of the electrical control panels. Our approach is based on the combination of Deep Learning techniques with Answer Set Programming (ASP), and allows for identifying possible anomalies and errors in the final product even when a very limited amount of training data is available. The experiments conducted on a real test case provided by an Italian Company operating in electrical control panel production demonstrate the effectiveness of the proposed approach.

Estilos ABNT, Harvard, Vancouver, APA, etc.

35

Beckmann, Pierre, Guillaume Köstner, and Inês Hipólito. "An Alternative to Cognitivism: Computational Phenomenology for Deep Learning." Minds and Machines, June 29, 2023. http://dx.doi.org/10.1007/s11023-023-09638-w.

Texto completo da fonte

Resumo:

AbstractWe propose a non-representationalist framework for deep learning relying on a novel method computational phenomenology, a dialogue between the first-person perspective (relying on phenomenology) and the mechanisms of computational models. We thereby propose an alternative to the modern cognitivist interpretation of deep learning, according to which artificial neural networks encode representations of external entities. This interpretation mainly relies on neuro-representationalism, a position that combines a strong ontological commitment towards scientific theoretical entities and the idea that the brain operates on symbolic representations of these entities. We proceed as follows: after offering a review of cognitivism and neuro-representationalism in the field of deep learning, we first elaborate a phenomenological critique of these positions; we then sketch out computational phenomenology and distinguish it from existing alternatives; finally we apply this new method to deep learning models trained on specific tasks, in order to formulate a conceptual framework of deep-learning, that allows one to think of artificial neural networks’ mechanisms in terms of lived experience.

Estilos ABNT, Harvard, Vancouver, APA, etc.

36

Wu, Maonian, Bang Chen, Shaojun Zhu, Bo Zheng, Wei Peng, and Mingyi Zhang. "Neuro-symbolic recommendation model based on logic query." Knowledge-Based Systems, December 2023, 111311. http://dx.doi.org/10.1016/j.knosys.2023.111311.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

37

Rivas, Ariam, Diego Collarana, Maria Torrente, and Maria-Esther Vidal. "A neuro-symbolic system over knowledge graphs for link prediction." Semantic Web, June 7, 2023, 1–25. http://dx.doi.org/10.3233/sw-233324.

Texto completo da fonte

Resumo:

Neuro-Symbolic Artificial Intelligence (AI) focuses on integrating symbolic and sub-symbolic systems to enhance the performance and explainability of predictive models. Symbolic and sub-symbolic approaches differ fundamentally in how they represent data and make use of data features to reach conclusions. Neuro-symbolic systems have recently received significant attention in the scientific community. However, despite efforts in neural-symbolic integration, symbolic processing can still be better exploited, mainly when these hybrid approaches are defined on top of knowledge graphs. This work is built on the statement that knowledge graphs can naturally represent the convergence between data and their contextual meaning (i.e., knowledge). We propose a hybrid system that resorts to symbolic reasoning, expressed as a deductive database, to augment the contextual meaning of entities in a knowledge graph, thus, improving the performance of link prediction implemented using knowledge graph embedding (KGE) models. An entity context is defined as the ego network of the entity in a knowledge graph. Given a link prediction task, the proposed approach deduces new RDF triples in the ego networks of the entities corresponding to the heads and tails of the prediction task on the knowledge graph (KG). Since knowledge graphs may be incomplete and sparse, the facts deduced by the symbolic system not only reduce sparsity but also make explicit meaningful relations among the entities that compose an entity ego network. As a proof of concept, our approach is applied over a KG for lung cancer to predict treatment effectiveness. The empirical results put the deduction power of deductive databases into perspective. They indicate that making explicit deduced relationships in the ego networks empowers all the studied KGE models to generate more accurate links.

Estilos ABNT, Harvard, Vancouver, APA, etc.

38

Giunchiglia, Eleonora, Alex Tatomir, Mihaela Cătălina Stoian, and Thomas Lukasiewicz. "CCN+: A Neuro-symbolic Framework for Deep Learning with Requirements." International Journal of Approximate Reasoning, January 2024, 109124. http://dx.doi.org/10.1016/j.ijar.2024.109124.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

39

Santos, Henrique, Ke Shen, Alice M. Mulvehill, Mayank Kejriwal, and Deborah L. McGuinness. "A Theoretically Grounded Question Answering Data Set for Evaluating Machine Common Sense." Data Intelligence, October 24, 2023, 1–29. http://dx.doi.org/10.1162/dint_a_00234.

Texto completo da fonte

Resumo:

Abstract Achieving machine common sense has been a longstanding problem within Artificial Intelligence. Thus far, benchmark data sets that are grounded in a theory of common sense and can be used to conduct rigorous, semantic evaluations of common sense reasoning (CSR) systems have been lacking. One expectation of the AI community is that neuro-symbolic reasoners can help bridge this gap towards more dependable systems with common sense. We propose a novel benchmark, called Theoretically Grounded common sense Reasoning (TG-CSR), modeled as a set of question answering instances, with each instance grounded in a semantic category of common sense, such as space, time, and emotions. The benchmark is few-shot i.e., only a few training and validation examples are provided in the public release to avoid the possibility of overfitting. Results from recent evaluations suggest that TG-CSR is challenging even for state-of-the-art statistical models. Due to its semantic rigor, this benchmark can be used to evaluate the common sense reasoning capabilities of neuro-symbolic systems.

Estilos ABNT, Harvard, Vancouver, APA, etc.

40

Mileo, Alessandra. "Towards a neuro-symbolic cycle for human-centered explainability." Neurosymbolic Artificial Intelligence, August 28, 2024, 1–13. http://dx.doi.org/10.3233/nai-240740.

Texto completo da fonte

Resumo:

Deep learning is being very successful in supporting humans in the interpretation of complex data (such as images and text) for critical decision tasks. However, it still remains difficult for human experts to understand how such results are achieved, due to the “black box” nature of the deep models used. In high-stake decision making scenarios such as the interpretation of medical imaging for diagnostics, such a lack of transparency still hinders the adoption of these techniques in practice. In this position paper we present a conceptual methodology for the design of a neuro-symbolic cycle to address the need for explainability and confidence (including trust) of deep learning models when used to support human experts in high-stake decision making, and we discuss challenges and opportunities in the implementation of such cycle as well as its adoption in real world scenarios. We elaborate on the need to leverage the potential of hybrid artificial intelligence combining neural learning and symbolic reasoning in a human-centered approach to explainability. We advocate that the phases of such a cycle should include i) the extraction of knowledge from a trained network to represent and encode its behaviour, ii) the validation of the extracted knowledge through commonsense and domain knowledge, iii) the generation of explanations for human experts, iv) the ability to map human feedback into the validated representation from i), and v) the injection of some of this knowledge in a non-trained network to enable knowledge-informed representation learning. The holistic combination of causality, expressive logical inference, and representation learning, would result in a seamless integration of (neural) learning and (cognitive) reasoning that makes it possible to retain access to the inherently explainable symbolic representation without losing the power of the deep representation. The involvement of human experts in the design, validation and knowledge injection process is crucial, as the conceptual approach paves the way for a new human–ai paradigm where the human role goes beyond that of labeling data, towards the validation of neural-cognitive knowledge and processes.

Estilos ABNT, Harvard, Vancouver, APA, etc.

41

Roig Vilamala, Marc, Tianwei Xing, Harrison Taylor, et al. "DeepProbCEP: A neuro-symbolic approach for complex event processing in adversarial settings." Expert Systems with Applications, December 2022, 119376. http://dx.doi.org/10.1016/j.eswa.2022.119376.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

42

EITER, THOMAS, NELSON HIGUERA, JOHANNES OETSCH, and MICHAEL PRITZ. "A Neuro-Symbolic ASP Pipeline for Visual Question Answering." Theory and Practice of Logic Programming, July 11, 2022, 1–16. http://dx.doi.org/10.1017/s1471068422000229.

Texto completo da fonte

Resumo:

Abstract We present a neuro-symbolic visual question answering (VQA) pipeline for CLEVR, which is a well-known dataset that consists of pictures showing scenes with objects and questions related to them. Our pipeline covers (i) training neural networks for object classification and bounding-box prediction of the CLEVR scenes, (ii) statistical analysis on the distribution of prediction values of the neural networks to determine a threshold for high-confidence predictions, and (iii) a translation of CLEVR questions and network predictions that pass confidence thresholds into logic programmes so that we can compute the answers using an answer-set programming solver. By exploiting choice rules, we consider deterministic and non-deterministic scene encodings. Our experiments show that the non-deterministic scene encoding achieves good results even if the neural networks are trained rather poorly in comparison with the deterministic approach. This is important for building robust VQA systems if network predictions are less-than perfect. Furthermore, we show that restricting non-determinism to reasonable choices allows for more efficient implementations in comparison with related neuro-symbolic approaches without losing much accuracy.

Estilos ABNT, Harvard, Vancouver, APA, etc.

43

Škrlj, Blaž, Jan Kralj, Janez Konc, Marko Robnik‐Šikonja, and Nada Lavrač. "Deep node ranking for neuro‐symbolic structural node embedding and classification." International Journal of Intelligent Systems, September 10, 2021. http://dx.doi.org/10.1002/int.22651.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

44

Abdullah, Iram, Ali Javed, Khalid Mahmood Malik, and Ghaus Malik. "DeepInfusion: A Dynamic Infusion based-Neuro-Symbolic AI Model for Segmentation of Intracranial Aneurysms." Neurocomputing, June 2023, 126510. http://dx.doi.org/10.1016/j.neucom.2023.126510.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

45

Hersche, Michael, Mustafa Zeqiri, Luca Benini, Abu Sebastian, and Abbas Rahimi. "A neuro-vector-symbolic architecture for solving Raven’s progressive matrices." Nature Machine Intelligence, March 9, 2023. http://dx.doi.org/10.1038/s42256-023-00630-8.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

46

Venigandla, Kamala, Navya Vemuri, and Naveen Vemuri. "Hybrid Intelligence Systems Combining Human Expertise and AI/RPA for Complex Problem Solving." International Journal of Innovative Science and Research Technology (IJISRT), April 5, 2024, 2066–75. http://dx.doi.org/10.38124/ijisrt/ijisrt24mar2039.

Texto completo da fonte

Resumo:

Hybrid Intelligence Systems (HIS) represent a paradigm shift in problem-solving methodologies by integrating human expertise with Artificial Intelligence (AI) and Robotic Process Automation (RPA). This paper explores the mechanisms, applications, benefits, challenges, and future directions of HIS in the context of complex problem-solving. Through collaborative synergies between human cognition and machine intelligence, HIS enhances decision-making accuracy, efficiency, and innovation. Human experts contribute domain knowledge, contextual understanding, and ethical reasoning, while AI algorithms and RPA systems offer data-driven insights, computational power, and process automation capabilities. HIS fosters inclusivity, diversity, and democratization in problem-solving processes by harnessing the collective intelligence of diverse teams and stimulating interdisciplinary collaboration. However, challenges such as privacy concerns, data security risks, and algorithmic biases must be addressed to realize the full potential of HIS. Looking ahead, the integration of Explainable AI (XAI), Edge AI, and Neuro symbolic AI holds promise for enhancing transparency, interpretability, and robustness in HIS architectures. Human-centered design principles and interdisciplinary research collaborations will shape the development and deployment of HIS, ensuring alignment with human values, preferences, and needs. Ultimately, HIS will continue to serve as a beacon of collaboration, creativity, and collective intelligence in shaping a better world for generations to come.

Estilos ABNT, Harvard, Vancouver, APA, etc.

47

Hamilton, Kyle, Aparna Nayak, Bojan Božić, and Luca Longo. "Is neuro-symbolic AI meeting its promises in natural language processing? A structured review." Semantic Web, November 9, 2022, 1–42. http://dx.doi.org/10.3233/sw-223228.

Texto completo da fonte

Resumo:

Advocates for Neuro-Symbolic Artificial Intelligence (NeSy) assert that combining deep learning with symbolic reasoning will lead to stronger AI than either paradigm on its own. As successful as deep learning has been, it is generally accepted that even our best deep learning systems are not very good at abstract reasoning. And since reasoning is inextricably linked to language, it makes intuitive sense that Natural Language Processing (NLP), would be a particularly well-suited candidate for NeSy. We conduct a structured review of studies implementing NeSy for NLP, with the aim of answering the question of whether NeSy is indeed meeting its promises: reasoning, out-of-distribution generalization, interpretability, learning and reasoning from small data, and transferability to new domains. We examine the impact of knowledge representation, such as rules and semantic networks, language structure and relational structure, and whether implicit or explicit reasoning contributes to higher promise scores. We find that systems where logic is compiled into the neural network lead to the most NeSy goals being satisfied, while other factors such as knowledge representation, or type of neural architecture do not exhibit a clear correlation with goals being met. We find many discrepancies in how reasoning is defined, specifically in relation to human level reasoning, which impact decisions about model architectures and drive conclusions which are not always consistent across studies. Hence we advocate for a more methodical approach to the application of theories of human reasoning as well as the development of appropriate benchmarks, which we hope can lead to a better understanding of progress in the field. We make our data and code available on github for further analysis.11 https://github.com/kyleiwaniec/neuro-symbolic-ai-systematic-review

Estilos ABNT, Harvard, Vancouver, APA, etc.

48

Chalvatzaki, Georgia, Ali Younes, Daljeet Nandha, An Thai Le, Leonardo F. R. Ribeiro, and Iryna Gurevych. "Learning to reason over scene graphs: a case study of finetuning GPT-2 into a robot language model for grounded task planning." Frontiers in Robotics and AI 10 (August 15, 2023). http://dx.doi.org/10.3389/frobt.2023.1221739.

Texto completo da fonte

Resumo:

Long-horizon task planning is essential for the development of intelligent assistive and service robots. In this work, we investigate the applicability of a smaller class of large language models (LLMs), specifically GPT-2, in robotic task planning by learning to decompose tasks into subgoal specifications for a planner to execute sequentially. Our method grounds the input of the LLM on the domain that is represented as a scene graph, enabling it to translate human requests into executable robot plans, thereby learning to reason over long-horizon tasks, as encountered in the ALFRED benchmark. We compare our approach with classical planning and baseline methods to examine the applicability and generalizability of LLM-based planners. Our findings suggest that the knowledge stored in an LLM can be effectively grounded to perform long-horizon task planning, demonstrating the promising potential for the future application of neuro-symbolic planning methods in robotics.

Estilos ABNT, Harvard, Vancouver, APA, etc.

49

Wickramarachchi, Ruwan, Cory Henson, and Amit Sheth. "Knowledge-infused Learning for Entity Prediction in Driving Scenes." Frontiers in Big Data 4 (November 25, 2021). http://dx.doi.org/10.3389/fdata.2021.759110.

Texto completo da fonte

Resumo:

Scene understanding is a key technical challenge within the autonomous driving domain. It requires a deep semantic understanding of the entities and relations found within complex physical and social environments that is both accurate and complete. In practice, this can be accomplished by representing entities in a scene and their relations as a knowledge graph (KG). This scene knowledge graph may then be utilized for the task of entity prediction, leading to improved scene understanding. In this paper, we will define and formalize this problem as Knowledge-based Entity Prediction (KEP). KEP aims to improve scene understanding by predicting potentially unrecognized entities by leveraging heterogeneous, high-level semantic knowledge of driving scenes. An innovative neuro-symbolic solution for KEP is presented, based on knowledge-infused learning, which 1) introduces a dataset agnostic ontology to describe driving scenes, 2) uses an expressive, holistic representation of scenes with knowledge graphs, and 3) proposes an effective, non-standard mapping of the KEP problem to the problem of link prediction (LP) using knowledge-graph embeddings (KGE). Using real, complex and high-quality data from urban driving scenes, we demonstrate its effectiveness by showing that the missing entities may be predicted with high precision (0.87 Hits@1) while significantly outperforming the non-semantic/rule-based baselines.

Estilos ABNT, Harvard, Vancouver, APA, etc.

50

Abubakar, Hamza. "An optimal representation of Random Maximum kSatisfiability on a Hopfield Neural Network for High order logic(k 3)." Kuwait Journal of Science, December 1, 2021. http://dx.doi.org/10.48129/kjs.11861.

Texto completo da fonte

Resumo:

This paper proposed a new logical rule by incorporating Random maximum kSatsifiability (RANMAXkSAT) in the Hopfield neural network (HNN) as a single network model (HNN-RANMAXkSAT). The purpose is to combine the optimization capacity of the Hopfield neural network (HNN) for optimal representation to random maximum kSatsifiability (MAXRANkSAT). The energy function of a Hopfield neural network has been considered as a programming language for dynamics minimization mechanism. Several optimization and search problems associated with machine learning (ML), decision Science (DS) and artificial intelligence (AI) have been expressed on the Hopfield neural network(HNN) optimally by modelling the problem into variables to minimize the objective function that corresponds to Lyapunov energy function. The computer simulation has been developed based on RANMAXkSAT to explore the feasibility of a Hopfield neural network as a neuro-symbolic integration model in carrying out RANMAXkSAT logic programming optimally. The proposed model has been compared with the existing models published in the literature in term of Global minimum ratio (zM), Fitness energy landscapes (FEL), Root Means square error (RMSE), Mean absolute errors and computation time (CPU). Hence, based on the experimental simulation results, it revealed that the RANMAXkSAT can optimally and effectively represented in the Hopfield neural network (HNN) with 85.1 % classification accuracy.

Estilos ABNT, Harvard, Vancouver, APA, etc.

Artigos de revistas sobre o tema "Neuro-Symbolic Artificial intelligence"

Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos