Let the AI Do the Talk: Adventures with Natural Language Generation

6:30pm - Doors open & Networking

7pm-7:45 Marco Bonzanini : Let the AI Do the Talk: Adventures with Natural Language Generation (inc Q&A)

Recent advances in Artificial Intelligence have shown how computers can compete with humans in a variety of mundane tasks, but what happens when creativity is required?

This talk introduces the concept of Natural Language Generation, the task of automatically generating text, for examples articles on a particular topic, poems that follow a particular style, or speech transcripts that express some attitude. Specifically, we'll discuss the case for Recurrent Neural Networks, a family of algorithms that can be trained on sequential data, and how they improve on traditional language models.

The talk is for beginners, we'll focus more on the intuitions behind the algorithms and their practical implications, and less on the mathematical details. Practical examples with Python will showcase Keras, a library to quickly prototype deep learning architectures.

7:50pm-8:20pm - Yasir Ekinci: 'Demystifying complex models: Learnings from using SHAP explainers in the real world at GoCardless.' (inc Q&A)

Complex algorithms (GBDTs, deep neural nets, etc.) have the ability to perform far better than linear models because of they can capture non-linear behaviour and interaction effects.
However, interpreting these models was typically more difficult or in some cases (e.g. neural nets) even impossible.
For ML applications where explainability on the local (individual) level was key, this meant we were until recently limited to linear algorithms like Logistic Regression.

Recently we have seen advances in using simpler, locally interpretable models that are trained on top of the outputs of complex models.
SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model.

In this talk, we will share our experience of using SHAP in a real-world ML application, the changes we made to both our training and prediction phases and considerations to take into account when using SHAP.

8:20pm-9pm - Networking