Geoffrey Hinton talk "What is wrong with convolutional neural nets ?"

推荐理由

Hinton explains the concept of capsules in this video

推荐dr_zoidberg · 原文2017年11月

说明

这是2017年由trwappers发布的一部课堂讲座，主题归在Machine learning & deep learning。它讲的是capsule networks这一支里的具体问题，而不是把整个领域扫一遍。适合想看推导、证明或实现细节的人。内容上可以概括成：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.这些读者给出的理由，核心是：Recommended as Hinton's own explanation of capsule networks and his critique of pooling in CNNs.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2017年到2018年，有2位不同的读者在2个不同月份把它推荐出来，其中明确叫别人去看的有0次。节奏接近上课，可以暂停做笔记。它假设你愿意跟着一条推导走完。如果已经会了基本定义，就把注意力放在它怎么把capsule networks变成能跟着复述的例子。

视频信息

频道

trwappers

时长

1 小时 11 分

发布年份

2017

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)