What can be learnt with wide convolutional neural networks?

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.

Research in artificial intelligence (AI) and neural network (NN) technologies has been boosted by recent hardware advances, while the emergence of self-synthesized materials such as nanocarbons has attracted much attention to overcome the limitations of Si ...

This special issue explores the burgeoning field of deep learning for remote sensing time series analysis. The 20 contributed papers showcase diverse applications, including land cover mapping, change detection, atmospheric and biophysical/biochemical para ...

The rapid progress in machine learning in recent years has been based on a highly productive connection to gradient-based optimization. Further progress hinges in part on a shift in focus from pattern recognition to decision-making and multi-agent problems ...

The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

The crowdedness of the RF spectrum constitutes problems in communication, however it also accommodates large amount of useful information. This information can be used to determine existing signals and operating contexts. However, spectrum condition varies ...

Interacting systems are ubiquitous in nature and engineering, ranging from particle dynamics in physics to functionally connected brain regions. Revealing interaction laws is of fundamental importance but also particularly challenging due to underlying con ...

The need for high-quality automated seizure detection algorithms based on electroencephalography (EEG) becomes ever more pressing with the increasing use of ambulatory and long-term EEG monitoring. Heterogeneity in validation methods of these algorithms in ...

Modern optimization is tasked with handling applications of increasingly large scale, chiefly due to the massive amounts of widely available data and the ever-growing reach of Machine Learning. Consequently, this area of research is under steady pressure t ...

Differentiable rendering (DR) is an emerging field that facilitates the calculation and propagation of gradients of 3D objects through images. In contrast to deep neural networks (DNNs), which generally lack the understanding of 3D objects that form the im ...

The goal of this paper is to characterize function distributions that general neural networks trained by descent algorithms (GD/SGD), can or cannot learn in polytime. The results are: (1) The paradigm of general neural networks trained by SGD is poly-time ...

Background and objectives: Parameter estimation and uncertainty quantification are crucial in computa-tional cardiology, as they enable the construction of digital twins that faithfully replicate the behavior of physical patients. Many model parameters reg ...

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but requir ...

We introduce contextual stochastic bilevel optimization (CSBO) -- a stochastic bilevel optimization framework with the lower-level problem minimizing an expectation conditioned on some contextual information and the upper-level decision variable. This fram ...

In light of the pressing need for practical materials and molecular solutions to renewable energy and health problems, to name just two examples, one wonders how to accelerate research and development in the chemical sciences, so as to address the time it ...

Biomass resources can play an important role in the energy transition, being a dynamic feedstock that can be transformed either into solid, liquid or gaseous fuels. The biomass gasification is a versatile way to convert wastes into energy. In this work, th ...

With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance. Nevertheless, state-of ...

Most available studies on distributed GAN architectures focus on implementations with a fusion center. In this work, we propose a fully decentralized scheme by employing a diffusion strategy to train a network of GANs. We interpret the training procedure a ...

Animal behavior emerges from an interaction between neural network dynamics, musculoskeletal properties and the physical environment. Accessing and understanding the interplay between these elements requires the development of integrative and morphological ...

Tractography enables identifying and evaluating the healthy and diseased brain's white matter pathways from diffusion-weighted magnetic resonance imaging data. As previous evaluation studies have reported significant false-positive estimation biases, recen ...

Spending an uncontrolled quantity and quality of time on digital news and social media platforms can negatively influence mental health and decrease cognitive abilities. In this paper, we propose a sequential news recommendation system employing deep reinf ...

What can be learnt with wide convolutional neural networks?

Chat with Graph Search

Split weight distribution learning for binary neural networks exploiting nano-memristive graphene/sumanene/graphene devices

Preface: Advancing deep learning for remote sensing time series data analysis

A gentle introduction to gradient-based optimization and variational inequalities for machine learning

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

Intelligent RF System for Ultra Low Power Spectrum Sensing with Machine Learning

Collective relational inference for learning heterogeneous interactions

SzCORE: Seizure Community Open-Source Research Evaluation framework for the validation of electroencephalography-based automated seizure detection algorithms

Scalable constrained optimization

Inverse Rendering for PET Image Reconstruction

Polynomial-time universality and limitations of deep learning

Fast and robust parameter estimation with uncertainty quantification for the cardiac function

Training Efficient Controllers via Analytic Policy Gradient

Contextual Stochastic Bilevel Optimization

Accelerated chemical science with AI

Comparison of regression techniques for generating surrogate models to predict the thermodynamic behavior of biomass gasification systems

Adversarial training with informed data selection

Decentralized Gan Training Through Diffusion Learning

NeuroMechFly, a neuromechanical model of adult Drosophila melanogaster

Evaluating reproducibility and subject-specificity of microstructure-informed connectivity

Is Your Time Well Spent Online?: Focusing on Quality Experiences Through a User-Centered Recommendation Algorithm and Simulation Model