Yesterday we had the pleasure of partnering with non-profit organisation R-Ladies and luxury fashion ecommerce platform Farfetch to bring you Interpretable Deep Learning, with Keynote speaker Dr Shirin Glander.

The first of many, our latest event stemming from our partnership with R-Ladies was inspired by a lack of diversity in the tech industry, in particular, the Data Science and R community. As a Tech recruitment agency, we’re used to seeing a constant underrepresentation of minority genders in every role. So as a diversity initiative, we wanted to help R-ladies on their mission to achieve proportionate representation by encouraging, inspiring, and empowering people of genders currently underrepresented in the R community.

The Talk

Dr Shirin Glander, a data scientist at codecentric, came all the way from Munster, Germany to present a fascinating talk about 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. It’s minimalistic, efficient and highly flexible because it works with a modular layer system to define, compile and fit neural networks. Keras has been written in Python but is multifunctional and can also be used from within R. Because the underlying backend can be changed from TensorFlow to Theano and CNTK (with more options being developed right now) it is designed to be framework-independent. Models can be trained on CPU or GPU, locally or in the cloud.

Dr Shirin Glander, showed the community of aspiring data scientists and those embedded in the industry, how to build an image classifier with Keras, using a convolutional neural net to classify fruits in images. Not only that, Dr Shirin introduced Local Interpretable Model-agnostic Explanations – otherwise known as LIME, delving further into how the model works and how to apply it to image classifiers.

View the slideshow here

Interested in future events?

Whatever your gender, if you’re interested in R and Data Science, then attend these monthly meetups and embed yourself in the community.

Sign up to R-Ladies Meet Ups 

If you want to keep up to date with the latest industry insights or just need career advice, follow our company page:

LinkedIn

Twitter

Newsletter sign up

Name(Required)
This field is for validation purposes and should be left unchanged.