What is the practical impact?

Author(s): Francisco Utrera

Originally published on Towards AI.

We discovered a novel way to use adversarially-trained deep neural networks (DNNs) in the context of transfer learning to quickly achieve higher accuracy on image classification tasks — even when limited training data is available. You can read our paper at https://arxiv.org/abs/2007.05869.

Adversarial training modifies the typical DNN training procedure by adding an adversarial perturbation δᵢ on each input image xᵢ with the objective of generating DNNs robust to adversarial attacks. In particular, for a DNN with m input images, a loss function ℓ(⋅), a model-predicted response h(⋅) parametrized by θ, and the true label for the iᵗʰ image yᵢ, the… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI