17 citations · 39 across the 10 of their papers we have counts for
3 papers · 1 filter
Neural scaling laws for phenotypic drug discovery
Drew Linsley, John Griffin, Jason Parker Brown +5
Recent breakthroughs by deep neural networks (DNNs) in natural language processing (NLP) and computer vision have been driven by a scale-up of models and data rather than the disco…
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Drew Linsley, Pinyuan Feng, Thibaut Boissin +4
Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to c…
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Thomas Fel, Thibaut Boissin, Victor Boutin +9
Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability.…