Page 122 - Artificial Intelligence in the Age of Neural Networks and Brain Computing

CHAPTER

Evolving and Spiking

Connectionist Systems for 6

Brain-Inspired Artificial

Intelligence

Nikola Kasabov
Knowledge Engineering and Discovery Research Institute e KEDRI, Auckland University of
Technology, Auckland, New Zealand

CHAPTER OUTLINE
1. From Aristotle’s Logic to Artificial Neural Networks and Hybrid Systems................112
1.1 Aristotle’s Logic and Rule-Based Systems for Knowledge
Representation and Reasoning ............................................................. 112
1.2 Fuzzy Logic and Fuzzy RuleeBased Systems ......................................... 113
1.3 Classical Artificial Neural Networks (ANN)............................................. 114
1.4 Integrating ANN With Rule-Based Systems: Hybrid Connectionist
Systems ............................................................................................. 115
1.5 Evolutionary Computation (EC): Learning Parameter Values of ANN
Through Evolution of Individual Models as Part of Populations Over
Generations ........................................................................................ 116
2. Evolving Connectionist Systems (ECOS) ...............................................................117
2.1 Principles of ECOS.............................................................................. 117
2.2 ECOS Realizations and AI Applications ................................................. 118
3. Spiking Neural Networks (SNN) as Brain-Inspired ANN.........................................121
3.1 Main Principles, Methods, and Examples of
SNN and Evolving SNN (eSNN)............................................................ 121
3.2 Applications and Implementations of SNN for AI ................................... 124
4. Brain-Like AI Systems Based on SNN. NeuCube. Deep Learning Algorithms............125
4.1 Brain-Like AI Systems. NeuCube .......................................................... 125
4.2 Deep Learning and Deep Knowledge Representation in NeuCube
SNN Models: Methods and AI Applications ........................................... 127
4.2.1 Supervised Learning for Classification of Learned Patterns in a
SNN Model ................................................................................ 128
4.2.2 Semisupervised Learning ............................................................. 129

111
Artificial Intelligence in the Age of Neural Networks and Brain Computing. https://doi.org/10.1016/B978-0-12-815480-9.00006-2
Copyright © 2019 Elsevier Inc. All rights reserved.