Tensorflow and deep learning - without a PhD by Martin Görner
6 人推荐 · 跨 5 个月 · 2017–2020
中文导读
Martin Gorner 在 Devoxx 上的深度学习实战课。通过 MNIST 图像识别手把手带你手搓神经网络，覆盖网络架构选型，并现场诊断模型无法收敛的各种经典工程问题。
为什么 HN 推它
社区公认干货满满的实战派入门指南，短短两小时涵盖了大量学术教材往往略过的真实工程痛点与调优直觉。
「《无需博士学位的 TensorFlow 与深度学习》真的很棒，单单一场两小时的演讲就涵盖了海量干货。」HN 网友原话：Tensorflow and deep learning - without a PhD" is really good, and covers a lot of material in a single 2hr talk.
英文原摘要（HackerTube / Claude 整理）
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.
Repeatedly called an excellent, practical introduction that covers a lot in two hours and explains issues academic textbooks skip.
HN 上的提及
there's an excellent video from Martin Gorner at Google that describes a range of neural networks for MNIST[2]
If you haven't seen it check this out for an intro
This is a good introduction focused on tensorflow.
I watched a great video on Tensorflow (link below).
Tensorflow and deep learning - without a PhD" is really good, and covers a lot of material in a single 2hr talk.