Jay McClelland: Neural Networks and the Emergence of Cognition
Core Takeaways
Jay McClelland argues that neural networks provide a framework for understanding human cognition by mimicking biological processes.
Why it matters
This perspective challenges traditional cognitive psychology by emphasizing the biological basis of cognition, potentially reshaping AI development.
The backpropagation algorithm, developed by Rumelhart and Hinton, revolutionized neural network training by enabling error correction across multiple layers.
▶ 1:10:45
Why it matters
Backpropagation's efficiency in training neural networks has been pivotal in the AI and machine learning advancements we see today.
McClelland criticizes the current biomedical model of psychiatry, arguing it has not significantly advanced mental health treatment.
▶ 2:05:30
Why it matters
His critique suggests a need for more holistic approaches in psychiatry, which could lead to more effective treatments.
Ask this episode Deep
A preview of how Deep chat answers, grounded in this episode with citations and timestamps:
Cite this episode
For papers, blog posts, anywhere.
Related episodes
Where to go next from this conversation.
More on these ideas
John Hopfield: Physics View of the Mind and Neurobiology
Shares neural networks, evolution
1h 12m
Lisa Feldman Barrett: Counterintuitive Ideas About How the Brain Works
Shares evolution
2h 20m
Tomaso Poggio: Brains, Minds, and Machines
Shares neural networks
1h 20m
Matt Botvinick: Neuroscience, Psychology, and AI at DeepMind
More like this
2h
AI-generated summary · last refreshed 2026-06-06 05:34:40 · how we make these
Quotes are matched verbatim against the source transcript; references are checked to resolve to real URLs. Even so, AI can misread structure or attribute claims imperfectly. If you spot an error, please let us know.