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 Hacker News points people here: Repeatedly called an excellent, practical introduction that covers a lot in two hours and explains issues academic textbooks skip.
“Tensorflow and deep learning - without a PhD" is really good, and covers a lot of material in a single 2hr talk.”HN comment, 2018
“there's an excellent video from Martin Gorner at Google that describes a range of neural networks for MNIST[2]”
Excellent walkthrough of neural networks for MNIST with great source code.
Full comment
For Deep Learning, start with MNIST. The 1998 paper[1] describing LeNet goes into a lot more detail than more recent papers. Also there's an excellent video from Martin Gorner at Google that describes a range of neural networks for MNIST[2]. The source code used in his talk is excellent[3]. [1] link [2] this video [3] link
Strongly recommendsspeedplaneJun 2017
“I watched a great video on Tensorflow (link below).”
Intro to deep learning plus practical tips for diagnosing failing networks.
Full comment
I watched a great video on Tensorflow (link below). It mostly introduces very basic deep learning concepts, but there are a few key moments in the 2 hour+ video, where he explains what to do if something goes wrong. It's definitely not a "science", but with enough experience in deep learning, you can intuit what's going on inside the black box, and there are best practices on what to try next. For example, he goes through a few examples where a neural net has too many weights, or too little data or improperly connected nodes. All three result in problems, but the problems exhibit themselves in slightly different ways and with expertise you can start identifying them. this video
Strongly recommendseddieplan9Mar 2018
“Tensorflow and deep learning - without a PhD" is really good, and covers a lot of material in a single 2hr talk.”
Covers a lot of deep learning material in a single 2hr talk.
Full comment
For those interested in a deeper dive to just deep learning, "Tensorflow and deep learning - without a PhD" is really good, and covers a lot of material in a single 2hr talk. this video
Strongly recommendshalflingsJul 2020
“Explains a lot of very practical issues that you might not find in most academic textbooks”
Explains practical issues rarely found in academic textbooks.
Full comment
The video version [1] is also pretty awesome, though its code itself is a bit outdated now. Explains a lot of very practical issues that you might not find in most academic textbooks, but you encounter every day in practice. [1] this video
Recommendsandy_pppFeb 2017
“If you haven't seen it check this out for an intro”
Accessible intro to deep learning with TensorFlow.
Full comment
Amazing work; it makes using AI and Deep Learning accessible for everyone here really. If you haven't seen it check this out for an intro: this video I wish AMD graphics cards were supported fully. I really think AMD should find a way to work with the Tensor Flow team on this...
Recommendsgregatragenet3Feb 2017
“This is a good introduction focused on tensorflow.”
Good TensorFlow-focused introduction to deep neural networks.
Full comment
This is a good introduction focused on tensorflow. this video (Tensorflow and deep learning - without a PhD by Martin Görner) The ML/DNN rabbit-hole goes deep. If the video above leaves you wanting more, link does a good job on drilling into more specifics for the various techniques used. The examples on the tensorflow webpage are also very good.
