product iamge

Deep Cognitive Networks: Enhance Deep Learning by Modeling Human Cognitive Mechanism

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Download
Search on Amazon

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

Although deep learning models have achieved great progress in vision, speech, language, planning, control, and many other areas, there still exists a large performance gap between deep learning models and the human cognitive system. Many researchers argue that one of the major reasons accounting for the performance gap is that deep learning models and the human cognitive system process visual information in very different ways.

To mimic the performance gap, since 2014, there has been a trend to model various cognitive mechanisms from cognitive neuroscience, e.g., attention, memory, reasoning, and decision, based on deep learning models. This book unifies these new kinds of deep learning models and calls them deep cognitive networks, which model various human cognitive mechanisms based on deep learning models. As a result, various cognitive functions are implemented, e.g., selective extraction, knowledge reuse, and problem solving, for more effective information processing.

This book first summarizes existing evidence of human cognitive mechanism modeling from cognitive psychology and proposes a general framework of deep cognitive networks that jointly considers multiple cognitive mechanisms. Then, it analyzes related works and focuses primarily but not exclusively, on the taxonomy of four key cognitive mechanisms (i.e., attention, memory, reasoning, and decision) surrounding deep cognitive networks. Finally, this book studies two representative cases of applying deep cognitive networks to the task of image-text matching and discusses important future directions.


Author(s): Yan Huang, Liang Wang
Series: SpringerBriefs in Computer Science
Publisher: Springer
Year: 2023

Language: English
Pages: 72
City: Singapore

Preface
Acknowledgments
Contents
1 Introduction
1.1 Background
1.2 Content Organization
References
2 General Framework
2.1 Overview
2.2 Attention
2.3 Memory
2.4 Reasoning
2.5 Decision
2.6 Brief Summary
References
3 Attention-Based DCNs
3.1 Overview
3.2 Hard Attention
3.2.1 Sequential Attention
3.2.2 Transformable Attention
3.3 Soft Attention
3.3.1 Recurrent Attention
3.3.2 Cross-Modal Attention
3.3.3 Channel Attention
3.3.4 Self Attention
3.4 Brief Summary
References
4 Memory-Based DCNs
4.1 Overview
4.2 Short-Term Memory
4.2.1 Working Memory
4.2.2 Short-Term and Long-Term Memory
4.3 Long-Term Memory
4.3.1 Episodic Memory
4.3.2 Conceptual Memory
4.3.3 Semantic Memory
4.4 Brief Summary
References
5 Reasoning-Based DCNs
5.1 Overview
5.2 Analogical Reasoning
5.2.1 Memory Reasoning
5.2.2 Abstract Reasoning
5.3 Deductive Reasoning
5.3.1 Compositional Reasoning
5.3.2 Programmed Reasoning
5.4 Brief Summary
References
6 Decision-Based DCNs
6.1 Overview
6.2 Normative Decision
6.2.1 Sequential Decision
6.2.2 Group Decision
6.3 Descriptive Decision
6.3.1 Emotional Decision
6.3.2 Imitative Decision
6.4 Brief Summary
References
7 Conclusions and Future Trends
7.1 Conclusions
7.2 Open Problems and Future Trends
References