Deepmind artificial intelligence @ FDOT14

推荐理由

you learn more about the tech from a youtube video than from an article

推荐mturmon · 原文2014年12月

说明

这是2014年由Elizr发布的一部演示，主题归在Machine learning & deep learning。它讲的是deep reinforcement learning这一支里的具体问题，而不是把整个领域扫一遍。适合按兴趣直接看、不打算先补课的人。内容上可以概括成：A short smartphone-recorded clip from a 2014 event in Paris where DeepMind CEO Demis Hassabis presents an AI learning to play old Atari games. The system learns from only the video signal and the score. Audio quality is poor.这些读者给出的理由，核心是：HN commenters use it as the canonical demo of deep reinforcement learning, noting that watching it teaches more than an article does.它贴着当时的技术，看的时候要记得那是那个年份的判断。从2014年到2016年，有2位不同的读者在3个不同月份把它推荐出来，其中明确叫别人去看的有1次。适合先看结果再决定要不要深挖的人。先看它做成了什么。如果已经会了基本定义，就把注意力放在它怎么把deep reinforcement learning变成能跟着复述的例子。

视频信息

频道

Elizr

时长

4 分 41 秒

发布年份

2014

同主题更多

• The spelled-out intro to neural networks and backpropagation: building micrograd
• But what is a neural network? | Deep learning chapter 1
• AlphaGo - The Movie | Full award-winning documentary
• Transformers, the tech behind LLMs | Deep Learning Chapter 5
• USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?
• Lecture 1 | Machine Learning (Stanford)