Invariant Risk Minimisation for Cross-Organism Inference: Substituting Mouse Data for Human Data in Human Risk Factor Discovery

no code implementations • 14 Nov 2021 • Odhran O'Donoghue, Paul Duckworth, Giuseppe Ughi, Linus Scheibenreif, Kia Khezeli, Adrienne Hoarfrost, Samuel Budd, Patrick Foley, Nicholas Chia, John Kalantari, Graham Mackintosh, Frank Soboczenski, Lauren Sanders

In this work, we augment small human medical datasets with in-vitro data and animal models.

Mutual Information of Neural Network Initialisations: Mean Field Approximations

no code implementations • 8 Feb 2021 • Jared Tanner, Giuseppe Ughi

The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation.

Information Theory Information Theory

An Empirical Study of Derivative-Free-Optimization Algorithms for Targeted Black-Box Attacks in Deep Neural Networks

no code implementations • 3 Dec 2020 • Giuseppe Ughi, Vinayak Abrol, Jared Tanner

We perform a comprehensive study on the performance of derivative free optimization (DFO) algorithms for the generation of targeted black-box adversarial attacks on Deep Neural Network (DNN) classifiers assuming the perturbation energy is bounded by an $\ell_\infty$ constraint and the number of queries to the network is limited.

A Model-Based Derivative-Free Approach to Black-Box Adversarial Examples: BOBYQA

1 code implementation • 24 Feb 2020 • Giuseppe Ughi, Vinayak Abrol, Jared Tanner

We demonstrate that model-based derivative free optimisation algorithms can generate adversarial targeted misclassification of deep networks using fewer network queries than non-model-based methods.