Deep learning, concepts and frameworks: Find your way through the jungle (talk)

Today at OOP in Munich, I had an in-depth talk on deep learning, including applications, basic concepts as well as practical demos with Tensorflow, Keras and PyTorch.

As usual, the slides are on RPubs, split up into 2 parts because of the plenty of images included – lossy png compression did work wonders but there’s only so much you can expect 😉 – so there’s a part 1 and a part 2.

There’s also the github repository with the demo notebooks.

Thanks to everyone who attended, and thank you for the interesting questions!

Practical Deep Learning (talk)

Yesterday at IT Tage 2017, I had an introductory-level talk on deep learning.

After giving an overview of concepts and frameworks, I zoomed in on the task of image classification using Keras, Tensorflow and PyTorch, not aiming for high classification accuracy but wanting to convey the different “look and feel” of these frameworks.

(By sheer chance, the use case chosen happened to be about telling apart different types of endurance sports ;-))

Here are the slides, and here are the Jupyter notebooks.

Thanks to everyone who attended & thanks for reading!

Deep Learning in Action

On Wednesday at Hochschule München, Fakultät für Informatik and Mathematik I presented about Deep Learning (nbviewer, github, pdf).

Mainly concepts (what’s “deep” in Deep Learning, backpropagation, how to optimize …) and architectures (Multi-Layer Perceptron, Convolutional Neural Network, Recurrent Neural Network), but also demos and code examples (mainly using TensorFlow).

It was/is a lot material to cover in 90 minutes, and conceptual understanding / developing intuition was the main point. Of course, there is great online material to make use of, and you’ll see my preferences in the cited sources ;-).

Next year, having covered the basics, I hope to be developing use cases and practical applications showing applicability of Deep Learning even in non-Google-size (resp: Facebook, Baidu, Apple…) environments.
Stay tuned!


R for SQListas (3): Classifying Digits with TensorFlow

Yesterday at PASS Meetup Munich, I talked about R for SQListas – thanks again for your interest and attention guys, it was a very nice evening!
Actually, in addition to the content from that original presentation, which I’ve also covered in two recent blog posts (R for SQListas(1): Welcome to the tidyverse and R for SQListas(2): Forecasting the future), there was a new, third part this time: an introduction to machine learning with R, by example of the most classical of examples: MNIST, with a special focus on using rstudio’s tensorflow package for R.
While I hope I’ll find the time to write a post on this part too, I’m not too sure when this will be, so I’ve uploaded the slides already and added links to the pdf, github repo and publication on rpubs to the Presentations/Papers section. Enjoy!