Tensorflow and deep learning - without a PhD by Martin Görner

Channel:Devoxx · Length:2:35:53 · Published:2016-11-09 · Views:610133

Watch on YouTube

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 recommends it

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, 2018

Machine learning & deep learning · Computer vision, speech & NLP

Subtitles (excerpt)

hello everyone uh so thank you for coming for uh this university session on uh TensorFlow and and deep learning you're brave to come and spend uh three hours here with me um talking about neural networks TensorFlow and and all the nice things we can do with them [Music] um so let us start and yes maybe like this uh can you still hear me okay yes even in in the back everybody hears me perfect so let's go um I have quite a few things for you today of course we uh won't cover everything there is to cover in in neural networks and deep learning in this university session um but basically I' I've um I would like to walk you through uh two canonical examples um one which we'll do in this first session uh which is handwritten digit recognition and then in the second part of the session uh we will dive into recurrent neural networks um what I hope is that with this little dive in in in let's say three different types of neural networks you will have enough information to then go on your own and and read neural network blogs uh read the scientific papers and actually parse through the not always useful mathematics and formalism and understand the architectures that are being explained so let's dive uh right in this is a very classical data

On Hacker News

The video version [1] is also pretty awesome, though its code itself is a bit outdated now.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] [VIDEO] — halflings, 2020-07
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. [VIDEO] — eddieplan9, 2018-03
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. Fo… — speedplane, 2017-06
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] [VIDEO] [3] [LINK] — paulsutter, 2017-01
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: [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... — andy_ppp, 2017-02

Related videos