On the margins of source code: Video Lectures

Video lectures (with emphasis on courses rather than single lectures) that that I've (kind'a) watched, or have (barely) started watching but intend to finish -- as I enjoy them. ~~Some~~ Most of them are very simple! Try listening when doing house chores, it makes the time spent more fun.

Check out the course review portal Knollop.

NEW: Graduate Summer School: Deep Learning, Feature Learning at UCLA, 2012
2013 Fall: Advanced Topics in Programming Languages by Robert Harper
Introduction to Reinforcement Learning by Csaba Szepesvári
A Short Course on Reinforcement Learning by Satinder Singh Baveja
John Searle Philosophy of Mind and Philosophy of Language courses: Mind, Language
Large-Scale Machine Learning and Big Data by Yann LeCunn and John Langford
The Philosophy Of Mind by Marianne Talbot (Identity Theory, Non-Reductive Physicalism, Alternatives to Physicalism, Part 4, Q/A)
Introduction to Category Theory by error792
Introductory Machine Learning "Learning From Data" at Caltech by Yaser Abu-Mostafa
I've decided to link to some Lectures at Coursera

Neural Networks for Machine Learning by Geoffrey Hinton at University of Toronto
Artificial Intelligence Planning by Gerhard Wickler, Austin Tate at University of Edinburgh
Computer Vision: From 3D Reconstruction to Visual Recognition by Silvio Savarese, Fei-Fei Li at Stanford University
General Game Playing by Michael Genesereth at Stanford University
Natural Language Processing by Dan Jurafsky, Christopher Manning at Stanford University
Probabilistic Graphical Models by Daphne Koller at Stanford University
Computer Vision: The Fundamentals by Jitendra Malik at Berkeley (UoC)
Machine Learning by Andrew Ng at Stanford University
Functional Programming Principles in Scala by Martin Odersky at EPFL (Lousanne)
Machine Learning by Pedro Domingos at University of Washington
Compilers by Alex Aiken at Stanford University
Computational Neuroscience by Rajesh P. N. Rao and Adrienne Fairhall
Discrete Optimization by Pascal Van Hentenryck
Artificial Intelligence Planning by Dr. Gerhard Wickler and Austin Tate
Natural Language Processing by Michael Collins

100 most popular Machine Learning lectures at videolectures.net.
Introduction to Artificial Intelligence: Sebastian Thrun and Peter Norvig; AI course videos (the playlist can be accessed now); Wonderwhy-ER's list
Machine Learning at Stanford by Andrew Ng (Introduction to Machine Learning)
Game Theory (elementary) by Benjamin Polak at Yale
Online Learning, Regret Minimization, and Game Theory by Avrim Blum

contextual bandit Learning through Exploration by Alina Beygelzimer and John Langford

Statistical Learning Theory by John Shawe-Taylor: it's rather slow, the one-before-last video is missing and the last video has slides from the missing video instead so I gave up on watching the last vid; but it's a hands-on focused introduction to the PAC theory
Machine Learning Summer School 2011 - Bordeaux

Kernel Methods, Monte Carlo Methods, Bayesian Inference, Bayesian Nonparametrics, Sparse Methods for Under-determined Inverse Problems, Learning Theory: statistical and game-theoretic approaches, Graphical Models and message-passing algorithms

Foundations of Machine Learning by Marcus Hutter is a more fleshed-out variant of Universal Artificial Intelligence, the latter also shows recent approximations / experimental results (both are not going into details), see also Ray Solomonoff (read by Marcus Hutter) - Algorithmic Probability, Heuristic Programming and AGI
Heuristics, Probability and Causality: Judea Pearl Tribute Symposium
(Reinforcement learning by Scott Sanner), then Richard Sutton - AGI 10 Keynote Address (part 2), then Hamid Reza Maei - GQ(lambda)- A General Gradient Algorithm for Temporal-Difference Prediction Learning with Eligibility Traces
Deep Belief Networks by Geoffrey E. Hinton (or perhaps it was the old Google TechTalk version of this lecture); this TechTalk is a bit more recent; Unsupervised Feature Learning and Deep Learning by Andrew Ng (with sparse coding)
Probabilistic Programs: A New Language for AI by Noah Goodman (from AGI 2011)

How to Grow a Mind: Statistics, Structure and Abstraction by Josh Tenenbaum (from NIPS 2010)

Answer Set Solving in Practice: slides, part 1 [download], part 2 [download], part 3 [download], part 4 [download] (from Tutorials at IJCAI-11)
Introduction to Databases at Stanford
Lecture series on advanced (functional) programming concepts by Ralf Lämmel (ongoing, latest 5th) is really cool, a continuation of greenhorn-targeted Functional Programming Fundamentals by Erik Meijer (of which I recommend The Countdown Problem by Graham Hutton), see also A Quick Tour of Scala
Effective ML by Yaron Minsky (effective with people, i.e. elegant)
Monadic Design Patterns for the Web by Greg Meredith (ongoing, latest 3rd) is a monad tutorial like no other, see also Whiteboard Jam Session with Brian Beckman and Greg Meredith - Monads and Coordinate Systems (about zippers)
Oregon Programming Languages Summer School:

Logic, Languages, Compilation, and Verification, 2010
NEW: Types, Logic, and Verification, 2013

The Catsters -- NEW: Catsters guide (you might need to look up natural isomorphism first if you'd be confused by the notion of "isomorphism of functors")
Introduction to Algorithms by Erik Demaine and Charles Leiserson at MIT (elementary, but high quality and good selection of topics, I only missed a lecture about priority queues -- here NPTEL at IIT Delhi, also a lecture on tries -- a lecture on Fibonacci Heaps would be great)

Graphical Models and Variational Methods (also from Berder Island) by Christopher Bishop (the relevant part of Pattern Recognition and Machine Learning starts at chapter 8)
Introduction to causal discovery: A Bayesian Networks approach
Modern Physics: Statistical Mechanics by Leonard Susskind at Stanford (slow and sometimes handwavy, nice introduction of probability and entropy, nice treatment of phase transitions on "spin lattices")
Linear Dynamical Systems, then Convex Optimization by Stephen Boyd at Stanford University
Mining Sets of Patterns by Jilles Vreeken, Siegfried Nijssen, Bjorn Bringmann; here are slides to download (slides are not shown in the video and aren't synchronized)
Cognitive Science C102: Scientific Approaches to Consciousness at UC Berkeley (rather trivial, mostly cursory overview of experimental results); podcasts about consciousness:

Consciousness with Christof Koch (BSP 22)
Review: "On Being Certain" (BSP 42)
Meditation and the Brain with Daniel Siegel (BSP 44)
How our Brain Creates Our World with Chris Frith, PhD (BSP 57)
Interview with Philosopher Alva Noë (BSP 58) (has written a book " Out of Our Heads: Why You Are Not Your Brain, and Other Lessons from the Biology of Consciousness")
Affective Neuroscience with Jaak Panksepp (BSP 65)
Thomas Metzinger explores Consciousness (BSP 67)
Embodied Cognition with Lawrence Shapiro (BSP 73)
CPBD 082: Eric Schwitzgebel – The Unreliability of Naive Introspection
CPBD 085: Marcel Brass – The Neuroscience of Free Will

Brain Science Podcast in its entirety (mostly independent popular level podcasts, but otherwise great)
Introduction to Philosophy by Richard Brown; introduction via history of (western) philosophy -- mostly presocratics, Plato, Aristotle, Descartes, Hume, Kant.
Ethics and Moral Issues by Richard Brown; introduction to (meta)ethics.

The order in which the lectures were prepared puts egoism after Kant's deontology (and the discussion of freedom is somewhere in the beginning), but it doesn't pose problems. (Thomas Hobbes comes before Kant, Ayn Rand comes after.) It's a bit weaker than the above intro to philosophy.