Some of my written posts!


Natural adversaries and out-of-distribution detection

A brief look at a more ‘natural’ approach to adversarial attacks and whether they can be considered to be ‘within distribution’ of the original model.


Feature Visualisation Part 1

Making a start with feature visualisation! This is a really cool method when trying to interpret the information a network is learning.


Feature Visualisation Part 2

Discusses the more advanced aspects of feature visualisation improving on the previous part!


Rubbish Images

Looks at a particular weakness of neural networks when we give them out-of-distribution data to classify.