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。

GPT3: An Even Bigger Language Model - Computerphile
Rob Miles discusses GPT-3 on Computerphile, covering how scaling parameters kept improving results over GPT-2 and how the model nearly learned arithmetic without anyone knowing exactly how.

Polyworld: Using Evolution to Design Artificial Intelligence
A 2007 Google Tech Talk introducing Polyworld, an artificial life simulator used to evolve artificial intelligence by designing worlds rather than minds.

Google's DeepMind AI Just Taught Itself To Walk
A two-minute Insider Tech clip on DeepMind's simulated agents that learned to walk, run, jump and climb without guidance, with the goofy resulting gaits.

Tesla AI Day 2021
Tesla's 2021 AI Day presentation covering vision, planning and control, auto-labeling, simulation, the Dojo training hardware and the Tesla Bot announcement, followed by a Q&A.

A Style-Based Generator Architecture for Generative Adversarial Networks
A short demo video for NVIDIA's StyleGAN paper, which proposes a style-based generator for GANs.

Andrej Karpathy — “We’re summoning ghosts, not building animals”
Dwarkesh Patel interviews Andrej Karpathy on why reinforcement learning is flawed, why AGI may blend into steady GDP growth, why self-driving took so long, and the future of education.

The Day FPS Games Died
The video argues that machine-learning-based aimbots, which read the screen and drive the controls externally, could make cheating in FPS games undetectable.

WE MUST ADD STRUCTURE TO DEEP LEARNING BECAUSE...
Machine Learning Street Talk interviews Paul Lessard about Categorical Deep Learning, which uses category theory and monads to make neural network architectures more interpretable and composable.

world's best ai vs geoguessr pro
GeoGuessr pro Rainbolt plays head-to-head against an AI built by Stanford students that guesses locations from street-view images.

Teaching Robots New Behaviors
Toyota Research Institute presents an approach for teaching robots new dexterous behaviors from human demonstration.

NIPS 2017 Test of Time Award "Machine learning has become alchemy.” | Ali Rahimi, Google
Ali Rahimi accepts the NIPS 2017 Test of Time Award and argues that machine learning has become alchemy, with practice running ahead of understanding.