This book delves into the algorithms and architectures driving AI research, comparing them with biological brains to address deep conceptual issues in perception, memory, and control systems. It aims to bridge the gap between theories of biological brains and the practice of building artificial ones, grappling with longstanding controversies about intelligence and its biological inspiration.
This book provides a unified framework for understanding neurobiological systems by integrating concepts from neural coding, computation, physiology, communications theory, control theory, dynamics, and probability theory. It offers insights into neural function through detailed examples and discussions, making it valuable for neuroscientists and engineers alike.
In 'How to Build a Brain', Chris Eliasmith presents a detailed exploration of a new cognitive architecture that takes biological detail seriously while addressing cognitive phenomena. The book introduces the Semantic Pointer Architecture (SPA), which provides tools for constructing models of perception, cognition, and motor functions. It includes practical tutorials using the Nengo neural simulation environment to provide hands-on experience with the concepts presented.
Patreon: https://www.patreon.com/mlst
Discord: https://discord.gg/ESrGqhf5CB
Twitter: https://twitter.com/MLStreetTalk
Chris Eliasmith is a renowned interdisciplinary researcher, author, and professor at the University of Waterloo, where he holds the prestigious Canada Research Chair in Theoretical Neuroscience. As the Founding Director of the Centre for Theoretical Neuroscience, Eliasmith leads the Computational Neuroscience Research Group in exploring the mysteries of the brain and its complex functions. His groundbreaking work, including the Neural Engineering Framework, Neural Engineering Objects software environment, and the Semantic Pointer Architecture, has led to the development of Spaun, the most advanced functional brain simulation to date. Among his numerous achievements, Eliasmith has received the 2015 NSERC "Polany-ee" Award and authored two influential books, "How to Build a Brain" and "Neural Engineering."
Chris' homepage:
http://arts.uwaterloo.ca/~celiasmi/
Interviewers: Dr. Tim Scarfe and Dr. Keith Duggar
TOC:
Intro to Chris [00:00:00]
Continuous Representation in Biologically Plausible Neural Networks [00:06:49]
Legendre Memory Unit and Spatial Semantic Pointer [00:14:36]
Large Contexts and Data in Language Models [00:20:30]
Spatial Semantic Pointers and Continuous Representations [00:24:38]
Auto Convolution [00:30:12]
Abstractions and the Continuity [00:36:33]
Compression, Sparsity, and Brain Representations [00:42:52]
Continual Learning and Real-World Interactions [00:48:05]
Robust Generalization in LLMs and Priors [00:56:11]
Chip design [01:00:41]
Chomsky + Computational Power of NNs and Recursion [01:04:02]
Spiking Neural Networks and Applications [01:13:07]
Limits of Empirical Learning [01:22:43]
Philosophy of Mind, Consciousness etc [01:25:35]
Future of human machine interaction [01:41:28]
Future research and advice to young researchers [01:45:06]
Refs:
http://compneuro.uwaterloo.ca/publications/dumont2023.html
http://compneuro.uwaterloo.ca/publications/voelker2019lmu.html
http://compneuro.uwaterloo.ca/publications/voelker2018.html
http://compneuro.uwaterloo.ca/publications/lu2019.html
https://www.youtube.com/watch?v=I5h-xjddzlY
Machine Learning Street Talk (MLST) 
