Best Machine learning & deep learning Videos
「Machine learning & deep learning」下面有131部被不同的人、在不同月份推荐过的视频。挑的时候先看对象:入门25部,适合还没学过的人;进阶51部,适合已经懂术语的人;普通向38部,按兴趣就能看;更硬的17部,留给想看推导或细节的人。这一类数量最多的是演讲,所以它们的共同点是一位讲者把一个判断讲完,例子是为了撑住这个判断。常出现的频道包括Andrej Karpathy、3Blue1Brown、Google TechTalks。目录给这个主题划的范围是:Machine learning: neural networks, deep learning, backpropagation, training, optimization, reinforcement learning, AlphaGo, ML research lectures, Karpathy, Hinton, LeCun, Stanford CS231n.如果只看三部,就从《The spelled-out intro to neural networks and backpropagation: building micrograd》开始,它负责把问题讲出画面;然后看《But what is a neural network? | Deep learning chapter 1》,换一种讲法或例子;最后看《AlphaGo - The Movie | Full award-winning documentary》,留给已经有基础的人。页面按每页24部切开,顺序看的是被推荐跨越了多少个月,不是播放量。每条标题下面那一句是这部片子自己的内容说明,用来区分它在讲定义、过程、演示还是观点。点进去能看到推荐原话、原文链接和适合谁看。看的时候把强烈推荐当成有人明确叫你去看,把引用当成只是拿来举例,把批评留下来对照,不要把每条评论都当成同一力度。

Geoffrey Hinton in conversation with Fei-Fei Li — Responsible AI development
A 2023 University of Toronto conversation between Geoffrey Hinton and Fei-Fei Li on responsible AI development.

MENACE: the pile of matchboxes which can learn
Matt Parker of Stand-up Maths demonstrates MENACE, Donald Michie's 1961 machine made of matchboxes that learns to play noughts and crosses through reinforcement.

Recent Developments in Deep Learning
Geoff Hinton's 2010 Google Tech Talk on deep belief networks, learning layers of representation one at a time from unlabeled data, and extending them with multiplicative interactions.

AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
A Two Minute Papers episode on NVIDIA's recurrent denoising autoencoder, which cleans up noisy Monte Carlo path-traced image sequences.

AI Ethics, Impossibility Theorems and Tradeoffs - Chris Stucchio | Crunch 2018
Chris Stucchio presents the ethical principles behind algorithmic decision making and shows with examples from lending, criminology and education that they cannot all be satisfied at once.

Introducing Nx - José Valim | Lambda Days 2021
Jose Valim introduces Nx, the project bringing numerical computing to Elixir, covering multi-dimensional tensors, automatic differentiation and JIT compilation to CPU and GPU.

John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges
UC Berkeley EECS colloquium by OpenAI's John Schulman on reinforcement learning from human feedback.

Trends in Deep Learning Hardware: Bill Dally (NVIDIA)
Bill Dally of NVIDIA gives a University of Washington lecture on trends in deep learning hardware.

Google's DeepMind AI vs StarCraft 2 World Champion - Game 1
ArtosisTV's commentary on Game 1 of DeepMind's AlphaStar (Protoss) against top Zerg player Serral at Blizzcon 2019.

Full interview: "Godfather of artificial intelligence" talks impact and potential of AI
A 42-minute CBS interview with Geoffrey Hinton at the Vector Institute in 2023, covering the history of neural networks and the present and future of AI.

Why Can't AI Make Its Own Discoveries? — With Yann LeCun
Yann LeCun on the Big Technology Podcast discusses why current AI models cannot make discoveries despite their knowledge.

Geoffrey Hinton talk "What is wrong with convolutional neural nets ?"
Geoffrey Hinton gives an MIT talk on what is wrong with convolutional neural networks and introduces his capsules project.

Backpropagation calculus | Deep Learning Chapter 4
3Blue1Brown's chapter 4 on deep learning gives a more formal, symbol-based account of backpropagation calculus, connecting the intuition from the previous chapter to the math found in textbooks and code.

Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
The first lecture of Stanford's CS231n course on convolutional neural networks for visual recognition.

Chris Lattner: Compilers, LLVM, Swift, TPU, and ML Accelerators | Lex Fridman Podcast #21
Lex Fridman interviews Chris Lattner, creator of LLVM, Clang and Swift, about compilers, Swift for TensorFlow, TPUs and ML accelerators.

The Lighthill Debate (1973) - part 1 of 6
First part of a six-part recording of the 1973 Lighthill debate on AI, where Sir James Lighthill's critical report on AI research was contested by figures including McCarthy and Michie.

Training an unbeatable AI in Trackmania
Yosh trains a reinforcement learning agent to drive Trackmania until he can no longer beat it.

AI does not exist but it will ruin everything anyway
Physicist and YouTuber Angela Collier argues in this hour-long video that AI as commonly described does not really exist.

CS231n Winter 2016: Lecture1: Introduction and Historical Context
The first lecture of Stanford's CS231n Winter 2016 course on convolutional neural networks for visual recognition, introducing the course and the historical context of computer vision.

PREDATOR - Tracker that learns and improves
A demo of PREDATOR (TLD), a real-time object tracker that learns the appearance of its target and improves while it tracks.

Building Brains to Understand the World's Data
Jeff Hawkins presents his view that the neocortex works on principles different from traditional computers.

How AlphaZero Completely CRUSHED Stockfish
GothamChess walks through AlphaZero's famous games against Stockfish, highlighting its unusual pawn sacrifices and positional style.

Jim Keller - Moore's Law in the age of AI Chips
Jim Keller's talk at the 2020 Scaled Machine Learning conference on Moore's Law in the age of AI chips.

GradIEEEnt half decent: The hidden power of imprecise lines
Tom 7 (suckerpinch) delivers a long, comedic digression on gradient descent and floating-point imprecision.