Search Results for author:
Found 13 papers, 5 papers with code
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.
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
The distance to the support can be interpreted as a normality score, and its approximation using 1-Lipschitz neural networks provides robustness bounds against $l2$ adversarial attacks, an under-explored weakness of deep learning-based OCC algorithms.
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.
Precipitaion Nowcasting using Deep Neural Network
Precipitation nowcasting is of great importance for weather forecast users, for activities ranging from outdoor activities and sports competitions to airport traffic management.
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.
A Hölderian backtracking method for min-max and min-min problems
We present a new algorithm to solve min-max or min-min problems out of the convex world.
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.
Dyslexia and Dysgraphia prediction: A new machine learning approach
Learning disabilities like dysgraphia, dyslexia, dyspraxia, etc.
Estimation of conditional mixture Weibull distribution with right-censored data using neural network for time-to-event analysis
We propose a model based on the estimation of two-parameter Weibull distribution conditionally to the features.
From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
Some common concerns are identified and discussed such as the types of used representation, the roles of knowledge and data, the lack or the excess of information, or the need for explanations and causal understanding.
Learning Disentangled Representations via Mutual Information Estimation
In this paper, we investigate the problem of learning disentangled representations.
Learning Disentangled Representations of Satellite Image Time Series
In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data.
Predictive Interval Models for Non-parametric Regression
This work presents a new method to find two-sided predictive intervals for non-parametric least squares regression without the homoscedasticity assumption.
