Search Results for author:
Found 7 papers, 4 papers with code
Quantized Approximately Orthogonal Recurrent Neural Networks
Orthogonal recurrent neural networks (ORNNs) are an appealing option for learning tasks involving time series with long-term dependencies, thanks to their simplicity and computational stability.
DP-SGD Without Clipping: The Lipschitz Neural Network Way
To provide sensitivity bounds and bypass the drawbacks of the clipping process, we propose to rely on Lipschitz constrained networks.
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations. However, Saliency Maps generated by traditional neural networks are often noisy and provide limited insights.
Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks
Imposing orthogonality on the layers of neural networks is known to facilitate the learning by limiting the exploding/vanishing of the gradient; decorrelate the features; improve the robustness.
Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks
However they remain commonly considered as less accurate, and their properties in learning are still not fully understood.
White Paper Machine Learning in Certified Systems
Machine Learning (ML) seems to be one of the most promising solution to automate partially or completely some of the complex tasks currently realized by humans, such as driving vehicles, recognizing voice, etc.
Achieving robustness in classification using optimal transport with hinge regularization
This loss function has a direct interpretation in terms of adversarial robustness together with certifiable robustness bound.
