These are my sketchnotes for Sam Charrington’s podcast This Week in Machine Learning and AI about Adversarial Attacks Against Reinforcement Learning Agents with Ian Goodfellow & Sandy Huang: Sketchnotes from TWiMLAI talk: Adversarial Attacks Against Reinforcement Learning Agents with Ian Goodfellow & Sandy Huang You can listen to the podcast here. In this episode, I’m joined by Ian Goodfellow, Staff Research Scientist at Google Brain and Sandy Huang, Phd Student in the EECS department at UC Berkeley, to discuss their work on the paper Adversarial Attacks on Neural Network Policies.

Continue reading

When looking through the CRAN list of packages, I stumbled upon this little gem: pkgnet is an R library designed for the analysis of R libraries! The goal of the package is to build a graph representation of a package and its dependencies. And I thought it would be fun to play around with it. The little analysis I ended up doing was to compare dependencies of popular machine learning packages.

Continue reading

Here I am sharing the slides for a talk that my colleague Uwe Friedrichsen and I gave about Deep Learning - a Primer at the JAX conference on Tuesday, April 24th 2018 in Mainz, Germany. Slides can be found here: https://www.slideshare.net/ShirinGlander/deep-learning-a-primer-95197733 Deep Learning is one of the “hot” topics in the AI area – a lot of hype, a lot of inflated expectation, but also quite some impressive success stories.

Continue reading

These are my sketchnotes for Sam Charrington’s podcast This Week in Machine Learning and AI about Reproducibility and the Philosophy of Data with Clare Gollnick: Sketchnotes from TWiMLAI talk #121: Reproducibility and the Philosophy of Data with Clare Gollnick You can listen to the podcast here. In this episode, i’m joined by Clare Gollnick, CTO of Terbium Labs, to discuss her thoughts on the “reproducibility crisis” currently haunting the scientific landscape.

Continue reading

Since I migrated my blog from Github Pages to blogdown and Netlify, I wanted to start migrating (most of) my old posts too - and use that opportunity to update them and make sure the code still works. Here I am updating my very first machine learning post from 27 Nov 2016: Can we predict flu deaths with Machine Learning and R?. Changes are marked as bold comments. The main changes I made are:

Continue reading

On April 12th, 2018 I gave a talk about Explaining complex machine learning models with LIME at the Hamburg Data Science Meetup - so if you’re intersted: the slides can be found here: https://www.slideshare.net/ShirinGlander/hh-data-science-meetup-explaining-complex-machine-learning-models-with-lime-94218890 Traditional machine learning workflows focus heavily on model training and optimization; the best model is usually chosen via performance measures like accuracy or error and we tend to assume that a model is good enough for deployment if it passes certain thresholds of these performance criteria.

Continue reading

These are my sketchnotes for Sam Charrington’s podcast This Week in Machine Learning and AI about Systems and Software for Machine Learning at Scale with Jeff Dean: Sketchnotes from TWiMLAI talk #124: Systems and Software for Machine Learning at Scale with Jeff Dean You can listen to the podcast here. In this episode I’m joined by Jeff Dean, Google Senior Fellow and head of the company’s deep learning research team Google Brain, who I had a chance to sit down with last week at the Googleplex in Mountain View.

Continue reading