JNGannon ML Blog

This is blog about my experiments with machine learning. These are about artificial neural networks and adversarial noise. These are not an introduction to either of these topics.

Starts at the bottom, newer blogs at the top.

Github repository

About me

About the package

3. Combatting and detecting FGSM and PGD adversarial noise

Testing pre-trained pruned models against the RobustML framework for robustness and confidence estimates.

2. Output analysis

This blog looks at the output values of models used in blog 1. Outputs can be used to assess the quality of the images,

1. Pruning, cost functions and adversarial noise

My first blog, where I have changed the cost function and pruned weights using 2 different methods.