perception

A one-minute clip from Richard Feynman's 1979 Auckland lecture in which he answers whether you see an object or only its light. It is a short, playful take on perception and on the use of philosophy.

The opening lecture of Robert Sapolsky's Stanford course on Human Behavioral Biology, explaining the course premise and how to avoid categorical thinking. It starts a roughly 25-lecture series on how biology, genes, hormones and environment shape behavior.

Cognitive scientist George Lakoff lectures on how political debates are framed through language and metaphors tied to values, and on the moral worldviews behind progressive and conservative politics. It was given in 2005 at UC San Diego.

Stanford professor Robert Sapolsky lectures on depression as a real biological disease. He covers its biological and psychological causes, how it differs from ordinary sadness, and ideas such as learned helplessness. He ties these together into one account.

Douglas Hofstadter's Stanford Presidential Lecture argues that analogy is the core of cognition, illustrating how concepts, categorization and thought arise from analogy-making.

The first episode of John Vervaeke's lecture series on the modern meaning crisis, tracing its history through philosophy, cognitive science, religion and psychology. It introduces the series and its themes.

Robert Sapolsky's lecture on how the body's stress response, evolved for short-term physical emergencies, harms long-term health when triggered by psychological stressors. It was given as the inaugural Fenton-Rhodes Lecture.

Neuroscientist Anil Seth gives a Royal Institution lecture on the science of consciousness. He separates conscious level, content and self, and argues that experience arises from the brain's predictive inference.

Andrej Karpathy builds the GPT tokenizer from scratch, implementing byte pair encoding along with encode and decode. He shows how many odd LLM behaviors trace back to tokenization, and covers Unicode byte encodings along the way.

Leo Dirac explains how transformer models have replaced LSTMs in NLP. He gives background from bag of words through RNNs and LSTMs, then a technical deep dive into multi-headed self-attention and positional encoding, with sample code.

Daniel Dennett's Royal Institution lecture on whether the brain is a computer and where its software comes from. He argues that minds are built by evolution and culture, with competence arising without comprehension.

A 73-minute Stanford talk by Robert Sapolsky drawn from his book Behave. It surveys the biological factors behind human behavior at its best and worst.

The first lecture of Stanford's Natural Language Processing with Deep Learning course, taught by Chris Manning and Richard Socher. It introduces NLP and word vectors, including SVD, skip-gram, CBOW, negative sampling and word2vec.

Robert Sapolsky's Stanford lecture on language, comparing human and animal communication, ape language projects like Koko and Kanzi, and how language is acquired. It is part of his human behavioral biology course.

Dr. Russell Barkley lectures on the neuroanatomy of ADHD and how to treat it, linking executive function and working memory to the disorder. It is part 3 of a CADDAC series.

Peter Norvig's UBC distinguished lecture on how massive amounts of simple data, such as for language modeling, can yield understanding that hand-built models could not.

A Royal Institution lecture in which Nicholas Humphrey presents his theory of phenomenal consciousness and its evolution. He draws on the book Sentience and discusses evidence for animal sentience.

A clip of psychologist Jordan Peterson lecturing on intelligence and IQ, covering how it is defined and its correlation with academic and work success.

Andres Gomez Emilsson of the Qualia Research Institute presents a model of DMT experiences using hyperbolic geometry and dynamical systems theory. He describes how different intoxication levels correspond to changing curvature and information content of experience.

Noam Chomsky's 2011 University of Oslo lecture on Newton's contributions to the study of mind. He argues Newton abandoned mechanical explanation and lowered the bar for scientific intelligibility, with consequences for the limits of human understanding. Q&A starts at 45:33.

Sacha Arnoud, Waymo's Director of Engineering, gives a lecture in MIT's 2018 deep learning for self-driving cars course on the rise of machine learning in autonomous vehicles. It covers how Waymo uses deep learning and how it handles tricky driving situations.

Neuroscientist Karl Friston gives a 15-minute talk on the free energy principle, covering Markov blankets, Bayesian model evidence and global brain theories.

Douglas Hofstadter lectures at Uppsala University on how analogy and daring thinking drove Einstein's discovery of light quanta. He argues deep insight in physics comes from imaginative leaps rather than rigid logic.

A 2020 UC San Diego event with Roger Penrose and Stuart Hameroff presenting their Orch OR theory that consciousness arises from quantum processes in brain microtubules, followed by a conversation with Roger Bingham.

Robert Sapolsky's Stanford lecture on the biological underpinnings of religiosity, from his human behavioral biology course. It covers theories linking religion to stress, and schizotypal traits.

A short clip of Robert Sapolsky on how social hierarchy generates chronic stress, drawing on baboon research. It links rank-related stress to heart health and life expectancy.

A lecture by Swami Sarvapriyananda at IIT Kanpur on the Mandukya Upanishad and the question 'Who am I?'. It explains the four states of consciousness in Advaita Vedanta.

Geoffrey Hinton gives an MIT talk on what is wrong with convolutional neural networks and introduces his capsules project. The description points to the capsule network papers.

The first lecture of Stanford's CS231n course on convolutional neural networks for visual recognition. It surveys the history and key challenges of computer vision, from the Cambrian explosion and Hubel and Wiesel to ImageNet.

Robert Sapolsky's Stanford lecture on the limbic system as the emotional part of the nervous system, covering its role in decision making, links to the cortex and the functions of its subparts.

Robert Sapolsky's Stanford lecture on chaos and reductionism, which he calls one of the hardest of the course. It examines the limits of breaking systems into parts to understand them and introduces chaotic systems.

An excerpt of Richard Feynman's 1985 lecture Q&A about whether machines can think. He discusses the difficulty of defining what computers can never do and compares machine intelligence to machines that don't copy animals.