Tensorflow and deep learning - without a PhD by Martin Görner

推荐理由

Tensorflow and deep learning - without a PhD" is really good, and covers a lot of material in a single 2hr talk.

强烈推荐eddieplan9 · 原文2018年3月

说明

这是2016年由Devoxx发布的一部教程，主题归在Machine learning & deep learning。它讲的是deep learning with tensorflow这一支里的具体问题，而不是把整个领域扫一遍。适合第一次接触、还没有先修课的人。内容上可以概括成：Martin Gorner's Devoxx talk introduces deep learning with TensorFlow, walking through neural networks for MNIST, how to choose an architecture and how to diagnose networks that fail to train.这些读者给出的理由，核心是：Repeatedly called an excellent, practical introduction that covers a lot in two hours and explains issues academic textbooks skip.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2020年，有6位不同的读者在5个不同月份把它推荐出来，其中明确叫别人去看的有4次。适合打开电脑跟着做的人。如果只听不练，这集的价值会少一半。如果已经会了基本定义，就把注意力放在它怎么把deep learning with tensorflow变成能跟着复述的例子。

视频信息

频道

Devoxx

时长

2 小时 35 分

发布年份

2016

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)