Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Reduced-order models (ROMs) are widely used in scientific computing to tackle high-dimensional systems. However, traditional ROM methods may only partially capture the intrinsic geometric characteristics of the data. These characteristics encompass the und ...

Approximate multipliers (AppMults) are widely employed in deep neural network (DNN) accelerators to reduce the area, delay, and power consumption. However, the inaccuracies of AppMults degrade DNN accuracy, necessitating a retraining process to recover acc ...

To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to generate instance-level explainable maps in a semantic segmentation scenario, suc ...

Recent years have been marked with the fast-pace diversification and increasing ubiquity of machine learning (ML) applications. Yet, a firm theoretical understanding of the surprising efficiency of neural networks (NNs) to learn from high-dimensional data ...

Machine-learning models based on a point-cloud representation of a physical object are ubiquitous in scientific applications and particularly well-suited to the atomic-scale description of molecules and materials. Among the many different approaches that h ...

Dynamic aperture is an important concept for the study of non-linear beam dynamics in circular accelerators. It describes the extent of the phase-space region where a particle's motion remains bounded over a given number of turns. Understanding the feature ...

Motivated by policy gradient methods in the context of reinforcement learning, we derive the first large deviation rate function for the iterates generated by stochastic gradient descent for possibly non-convex objectives satisfying a Polyak-Łojasiewicz co ...

Deep Neural Networks (DNNs) trained on proprietary company data offer a competitive edge for the owning entity. However, these models can be attractive to competitors (or malicious entities), who can copy or clone these proprietary DNN models to use them t ...

Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by users with varying orientat ...

Koopmans spectral functionals are a powerful extension of Kohn-Sham density-functional theory (DFT) that enables the prediction of spectral properties with state-of-the-art accuracy. The success of these functionals relies on capturing the effects of elect ...

Atomic simulations using machine learning interatomic potential (MLIP) have gained a lot of popularity owing to their accuracy in comparison to conventional empirical potentials. However, the transferability of MLIP to systems outside the training set pose ...

Background: Cardiac output is essential for patient management in critically ill patients. The state-of-the-art for cardiac output monitoring bears limitations that pertain to the invasive nature of the method, high costs, and associated complications. Hen ...

In this paper, we consider the optimisation of a time varying scalar field by a network of agents with no gradient information. We propose a composite control law, blending extremum seeking with formation control in order to converge to the extrema faster ...

Text-to-image models, such as Stable Diffusion, can generate high-quality images from simple textual prompts. With methods such as Textual Inversion, it is possible to expand the vocabulary of these models with additional concepts, by learning the vocabula ...

Occluded person re-identification (ReID) is a person retrieval task which aims at matching occluded person images with holistic ones. For addressing occluded ReID, part-based methods have been shown beneficial as they offer fine-grained information and are ...

Information derived from experiences is incorporated into the brain as changes to ensembles of cells, termed engram cells, which allow memory storage and recall. The mechanism by which those changes hold specific information is unclear. Here, we test the h ...

Integrating various reinforcements into 3D concrete printing (3DCP) is an efficient method to satisfy critical requirements for structural applications. This paper explores an explainable ensemble machine learning (EML) method to predict the bond failure m ...

Tropical deforestation is a major environmental problem with severe consequences such as carbon emissions or biodiversity loss. While much research focuses on monitoring and mapping deforestation, less attention is paid to understanding the various reasons ...

In healthcare, data privacy of patients regulations prohibits data from being moved outside the hospital, preventing international medical datasets from being centralized for AI training. Federated learning (FL) is a data privacy-focused method that trains ...

Traffic-responsive signal control is a cost-effective, easy-to-implement, network management strategy, bearing high potential to improve performance in heavily congested networks with dy-namic traffic characteristics. Max Pressure (MP) distributed control ...

Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

Chat with Graph Search

OPTIMAL TRANSPORT-INSPIRED DEEP LEARNING FRAMEWORK FOR SLOW-DECAYING KOLMOGOROV \bfitn-WIDTH PROBLEMS: EXPLOITING SINKHORN LOSS AND WASSERSTEIN KERNEL

Gradient Approximation of Approximate Multipliers for High-Accuracy Deep Neural Network Retraining

Exploiting XAI Maps to Improve MS Lesion Segmentation and Detection in MRI

High-dimensional learning of narrow neural networks

Wigner kernels: Body-ordered equivariant machine learning without a basis

Optimizing Dynamic Aperture Studies with Active Learning

A Large Deviations Perspective on Policy Gradient Algorithms

TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding

ConGeo: Robust Cross-View Geo-Localization Across Ground View Variations

Predicting electronic screening for fast Koopmans spectral functional calculations

Comparing transferability in neural network approaches and linear models for machine-learning interaction potentials

Cardiac output estimated from an uncalibrated radial blood pressure waveform: validation in an in-silico-generated population

Gradient free cooperative seeking of a moving source

VETIM: Expanding the Vocabulary of Text-to-Image Models only with Text

Body Part-Based Representation Learning for Occluded Person Re-Identification

Engram cell connectivity as a mechanism for information encoding and memory function

Reinforcement bond performance in 3D concrete printing: Explainable ensemble learning augmented by deep generative adversarial networks

Classification of Tropical Deforestation Drivers with Machine Learning and Satellite Image Time Series

Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems

Two-layer adaptive signal control framework for large-scale dynamically-congested networks: Combining efficient Max Pressure with Perimeter Control