Compendium of Neurosymbolic Artificial Intelligence / edited by Pascal Hitzler, Md Kamruzzaman Sarker, Aaron Eberhart.

Format:

Book

Contributor:

Hitzler, Pascal, editor.

Sarker, Md Kamruzzaman, editor.

Eberhart, Aaron, editor.

Series:

Frontiers in artificial intelligence and applications ; Volume 369.

Frontiers in Artificial Intelligence and Applications Series ; Volume 369

Language:

English

Subjects (All):

Artificial intelligence.

Neural networks (Computer science).

Physical Description:

1 online resource (706 pages)

Edition:

First edition.

Place of Publication:

Amsterdam Netherlands : IOS Press, [2023]

Summary:

If only it were possible to develop automated and trainable neural systems that could justify their behavior in a way that could be interpreted by humans like a symbolic system.The field of Neurosymbolic AI aims to combine two disparate approaches to AI; symbolic reasoning and neural or connectionist approaches such as Deep Learning.

Contents:

Intro

Title Page

Introduction

Contents

Chapter 1. The Roles of Symbols in Neural-Based AI: They Are Not What You Think!

Chapter 2. Neuro-Symbolic RDF and Description Logic Reasoners: The State-Of-The-Art and Challenges

Chapter 3. Architectural Patterns for Neuro-Symbolic AI

Chapter 4. Semantic Web Machine Learning Systems: An Analysis of System Patterns

Chapter 5. Boolean Connectives and Deep Learning: Three Interpretations

Chapter 6. Constructivist Machine Learning

Chapter 7. Neural-Symbolic Interaction and Co-Evolving

Chapter 8. Neuro-Causal Models

Chapter 9. Building Robust and Explainable AI with Commonsense Knowledge Graphs and Neural Models

Chapter 10. Connectionist Neuroarchitectures in Cognition and Consciousness Theory Based on Integrative (Synchronization) Mechanisms

Chapter 11. Autodidactic and Coachable Neural Architectures

Chapter 12. The Neural Blackboard Theory of Neuro-Symbolic Processing: Logistics of Access, Connection Paths and Intrinsic Structures

Chapter 13. Class Expression Learning with Multiple Representations

Chapter 14. Embedding-Based First-Order Rule Learning in Large Knowledge Graphs

Chapter 15. Lifted Relational Neural Networks: From Graphs to Deep Relational Learning

Chapter 16. Discovering Visual Concepts and Rules in Convolutional Neural Networks

Chapter 17. Approximate Answering of Graph Queries

Chapter 18. Enhancing Case-Based Reasoning with Neural Networks

Chapter 19. Neuro-Symbolic Spatio-Temporal Reasoning

Chapter 20. Neuro-Symbolic Architectures for Combinatorial Problems in Structured Output Spaces

Chapter 21. Neuro-Symbolic Semantic Learning for Chemistry

Chapter 22. Semantic Loss Functions for Neuro-Symbolic Structured Prediction

Chapter 23. Combining Symbolic and Deep Learning Approaches for Sentiment Analysis.

Chapter 24. Few-Shot Continual Learning Based on Vector Symbolic Architectures

Chapter 25. Learning Logic Explanations by Neural Networks

Chapter 26. Combining Sub-Symbolic and Symbolic Methods for Explainability

Chapter 27. Explaining CNNs Using Knowledge Extraction and Graph Analysis

Chapter 28. Effective Reasoning over Neural Networks Using Lukasiewicz Logic

Chapter 29. Latent Trees for Compositional Generalization

Chapter 30. Weakly Supervised Reasoning by Neuro-Symbolic Approaches

Author Index.

Notes:

Includes index.

Description based on: online resource; title from pdf title page (ProQuest Ebook Central, viewed on January 3, 2024).

Description based on print version record.

Description based on publisher supplied metadata and other sources.

ISBN:

1-64368-407-8

OCLC:

1397574840