视频加载失败？在 YouTube 打开 ↗
Martin Görner：TensorFlow与深度学习——无需博士学位
Tensorflow and deep learning - without a PhD by Martin Görner
AI 翻译，未经编辑审核
讲什么
Martin Görner 从 MNIST 网络讲到架构选择，并解释如何诊断网络无法训练的问题。
HN 网友推荐理由
HN 网友推荐理由：被反复称为实用的深度学习入门，也解释了学术教材常略过的问题。
摘要与推荐理由由 HackerTube 用 AI 生成，大榕 AI 翻译整理，未经编辑审核。
视频数据来源：HackerTube（https://hackertube.org），基于 Hacker News 社区推荐整理，依 ODC-By 1.0（https://opendatacommons.org/licenses/by/1-0/）许可使用。筛选与中文整理：大榕 darong.ai。
展开英文原文字段
Title
Tensorflow and deep learning - without a PhD by Martin Görner
Summary
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.
Why HN
Repeatedly called an excellent, practical introduction that covers a lot in two hours and explains issues academic textbooks skip.
Primary topic
deep learning with tensorflow