During my stay in London for the m3 conference, I also gave a talk at the R-Ladies London Meetup on Tuesday, October 16th, about one of my favorite topics: Interpretable Deep Learning with R, Keras and LIME. Keras is a high-level open-source deep learning framework that by default works on top of TensorFlow. Keras is minimalistic, efficient and highly flexible because it works with a modular layer system to define, compile and fit neural networks.
The last two days, I was in London for the M-cubed conference. Here are the slides from my talk about Explaining complex machine learning models with LIME: 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.
These are my sketchnotes for Sam Charrington’s podcast This Week in Machine Learning and AI about Evaluating Model Explainability Methods with Sara Hooker: Sketchnotes from TWiMLAI talk: Evaluating Model Explainability Methods with Sara Hooker You can listen to the podcast here. In this, the first episode of the Deep Learning Indaba series, we’re joined by Sara Hooker, AI Resident at Google Brain. I had the pleasure of speaking with Sara in the run-up to the Indaba about her work on interpretability in deep neural networks.
In our next MünsteR R-user group meetup on Tuesday, November 20th, 2018, titled Using R to help plan the future of transport, Mark Padgham will provide an overview of several inter-related R packages for analysing urban dynamics. You can RSVP here: http://meetu.ps/e/F7zDN/w54bW/f The primary motivation for developing these packages has been their use in Active Transport Futures - a group of researchers and coders striving to aid cities to better plan for futures in which active travel, particularly walking and cycling, plays an increasingly prominent role (lots of open source code at github.
A while ago, I wrote two blogposts about image classification with Keras and about how to use your own models or pretrained models for predictions and using LIME to explain to predictions. Recently, I came across this blogpost on using Keras to extract learned features from models and use those to cluster images. It is written in Python, though - so I adapted the code to R. You find the results below.
On Wednesday, September 26th, I gave a talk about ‘Decoding The Black Box’ at the Frankfurt Data Science Meetup. My slides were created with beautiful.ai and can be found here. DECODING THE BLACK BOX And finally we will have with us Dr.Shirin Glander, whom we were inviting for a long time back. Shirin lives in Münster and works as a Data Scientist at codecentric, she has lots of practical experience.
I have yet another Meetup talk to announce: On Wednesday, September 26th, I’ll be talking about ‘Decoding The Black Box’ at the Frankfurt Data Science Meetup. Particularly cool with this meetup is that they will livestream the event at www.youtube.com/c/FrankfurtDataScience! TALK#2: DECODING THE BLACK BOX And finally we will have with us Dr.Shirin Glander, whom we were inviting for a long time back. Shirin lives in Münster and works as a Data Scientist at codecentric, she has lots of practical experience.
- OLDER POSTS
- page 1 of 9