Episode

#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
listen on Spotify
2:38:22
Published: Mon Sep 20 2021
Description

Jay McClelland is a cognitive scientist at Stanford. Please support this podcast by checking out our sponsors: - Paperspace: https://gradient.run/lex to get $15 credit - Skiff: https://skiff.org/lex to get early access - Uprising Food: https://uprisingfood.com/lex to get $10 off 1st starter bundle - Four Sigmatic: https://foursigmatic.com/lex and use code LexPod to get up to 60% off - Onnit: https://lexfridman.com/onnit to get up to 10% off EPISODE LINKS: Jay's Website: https://stanford.edu/~jlmcc/ PODCAST INFO: Podcast website: https://lexfridman.com/podcast Apple Podcasts: https://apple.co/2lwqZIr Spotify: https://spoti.fi/2nEwCF8 RSS: https://lexfridman.com/feed/podcast/ YouTube Full Episodes: https://youtube.com/lexfridman YouTube Clips: https://youtube.com/lexclips SUPPORT & CONNECT: - Check out the sponsors above, it's the best way to support this podcast - Support on Patreon: https://www.patreon.com/lexfridman - Twitter: https://twitter.com/lexfridman - Instagram: https://www.instagram.com/lexfridman - LinkedIn: https://www.linkedin.com/in/lexfridman - Facebook: https://www.facebook.com/lexfridman - Medium: https://medium.com/@lexfridman OUTLINE: Here's the timestamps for the episode. On some podcast players you should be able to click the timestamp to jump to that time. (00:00) - Introduction (07:12) - Beauty in neural networks (11:31) - Darwin and evolution (17:16) - The origin of intelligence (23:58) - Explorations in cognition (30:02) - Learning representations by back-propagating errors (36:27) - Dave Rumelhart and cognitive modeling (49:30) - Connectionism (1:12:23) - Geoffrey Hinton (1:14:19) - Learning in a neural network (1:31:11) - Mathematics & reality (1:38:19) - Modeling intelligence (1:48:57) - Noam Chomsky and linguistic cognition (2:03:18) - Advice for young people (2:14:26) - Psychiatry and exploring the mind (2:27:04) - Legacy (2:32:53) - Meaning of life

Chapters
The speaker received low carb bread as a pitch for a podcast sponsorship and was skeptical about its taste, but despite loving bread, sticks to a low carb diet.
00:00 - 07:40 (07:40)
listen on Spotify
Low Carb, Alpha Brain
Summary

The speaker received low carb bread as a pitch for a podcast sponsorship and was skeptical about its taste, but despite loving bread, sticks to a low carb diet. The speaker also discusses their use of Alpha Brain for focus during deep work sessions.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
A discussion on the idea of hydraulic system in our bodies inspired by the discovery of the hydraulic system in gardens during the Renaissance.
07:42 - 14:35 (06:52)
listen on Spotify
Physiology
Summary

A discussion on the idea of hydraulic system in our bodies inspired by the discovery of the hydraulic system in gardens during the Renaissance. This helped in the understanding of sensory and motor systems in physiology.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The speaker discusses their fascination with the engineering perspective of human embryonic and brain development, particularly in regards to the similarities between the visual system of monkeys and humans.
14:35 - 27:42 (13:07)
listen on Spotify
Human Development
Summary

The speaker discusses their fascination with the engineering perspective of human embryonic and brain development, particularly in regards to the similarities between the visual system of monkeys and humans.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The development of neural networks as a form of parallel computation was revolutionary in the field of computer science and paved the way for machine learning applications we use today.
27:42 - 35:49 (08:07)
listen on Spotify
Artificial Neural Networks
Summary

The development of neural networks as a form of parallel computation was revolutionary in the field of computer science and paved the way for machine learning applications we use today. Jeffrey Hinton played a significant role in this development alongside other notable figures.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The podcast discusses the intersection between technology and psychology, highlighting a PhD student's journey in studying mathematical psychology at Stanford and building models of language representation and problem-solving.
35:51 - 43:02 (07:11)
listen on Spotify
Psychology
Summary

The podcast discusses the intersection between technology and psychology, highlighting a PhD student's journey in studying mathematical psychology at Stanford and building models of language representation and problem-solving.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The interactive activation model of letter perception is a model that uses neuron-like processing units to connect the different features, letters, and words in a sentence, ultimately allowing them to be correctly recognized by the brain.
43:02 - 51:00 (07:58)
listen on Spotify
Science and Technology
Summary

The interactive activation model of letter perception is a model that uses neuron-like processing units to connect the different features, letters, and words in a sentence, ultimately allowing them to be correctly recognized by the brain.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
Our thoughts emerge from the connections between our neurons, which create a graded and continuous process of abstraction.
51:00 - 1:00:30 (09:29)
listen on Spotify
Neuroscience
Summary

Our thoughts emerge from the connections between our neurons, which create a graded and continuous process of abstraction. We should not treat them as monolithic entities, as they are influenced by external forces that allow them to change over time.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
As Alzheimer's progresses, patients lose the ability to recognize animals and differentiate between similar breeds of dogs, eventually forgetting even lower frequency categories.
1:00:30 - 1:13:06 (12:35)
listen on Spotify
Alzheimer's
Summary

As Alzheimer's progresses, patients lose the ability to recognize animals and differentiate between similar breeds of dogs, eventually forgetting even lower frequency categories. Rommel Hart is an important figure in cognitive science who experienced this decline himself.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
Backpropagation is the process of using error signals from the output layer to adjust the weights of connections in earlier layers of a neural network.
1:13:06 - 1:19:34 (06:27)
listen on Spotify
Neural Networks
Summary

Backpropagation is the process of using error signals from the output layer to adjust the weights of connections in earlier layers of a neural network. This technique allows for more accurate predictions and has been used to train multi-layer neural networks.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The term computational intelligence is used to describe the field where researchers are interested in going beyond human intelligence and contributing to the understanding of the world’s reasoning itself using non-biological computational intelligence.
1:19:34 - 1:31:29 (11:55)
listen on Spotify
Computational Intelligence
Summary

The term computational intelligence is used to describe the field where researchers are interested in going beyond human intelligence and contributing to the understanding of the world’s reasoning itself using non-biological computational intelligence.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The development of formal systems in mathematics that allowed for the derivation of new truths from existing ones influenced the way humans think and reason abstractly.
1:31:29 - 1:54:22 (22:52)
listen on Spotify
Mathematics
Summary

The development of formal systems in mathematics that allowed for the derivation of new truths from existing ones influenced the way humans think and reason abstractly. This process of acculturation in a particular mode of thought creates an intuitive understanding of the world, similar to how we understand languages.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
A discussion on how concepts from psychology, particularly innate endowment and explanation of behaviors, can raise interesting and challenging questions.
1:54:22 - 2:11:13 (16:50)
listen on Spotify
Psychology
Summary

A discussion on how concepts from psychology, particularly innate endowment and explanation of behaviors, can raise interesting and challenging questions.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The speaker discusses the intersection of cognitive psychology and computational approaches to understand the human mind, and shares their disillusionment with the prescription medication and biochemistry-heavy approach of psychiatry.
2:11:13 - 2:22:23 (11:10)
listen on Spotify
Cognitive Psychology
Summary

The speaker discusses the intersection of cognitive psychology and computational approaches to understand the human mind, and shares their disillusionment with the prescription medication and biochemistry-heavy approach of psychiatry.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The joy of science lies in the moment where scientific progress is built on a formal thought that is crystallized in discourse by one person, according to a researcher.
2:22:23 - 2:32:49 (10:25)
listen on Spotify
Science
Summary

The joy of science lies in the moment where scientific progress is built on a formal thought that is crystallized in discourse by one person, according to a researcher. The continuous way of thinking about things makes the transition to scientific progress less apparent for some and more exciting for others.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast
The creation of efforts to reify meaning in religious traditions is just a part of the expression of that goal that we have to not find out what the meaning is but to make it ourselves.
2:32:49 - 2:38:17 (05:28)
listen on Spotify
Philosophy
Summary

The creation of efforts to reify meaning in religious traditions is just a part of the expression of that goal that we have to not find out what the meaning is but to make it ourselves.

Episode
#222 – Jay McClelland: Neural Networks and the Emergence of Cognition
Podcast
Lex Fridman Podcast