Deterministic equivalent and error universality of deep random features learning

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the second-order tota ...

Neural Networks (NNs), renowned for their universal approximation capabilities, have proven well-suited for parametrizing nonlinear control policies and modeling complex processes from available data. However, several NN architectures are physics-agnostic, ...

Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle in dense tasks like zero-shot open-vocabulary segmentation. This deficiency ...

We consider the problem of learning to play a repeated contextual game with unknown reward and unknown constraints functions. Such games arise in applications where each agent’s action needs to belong to a feasible set, but the feasible set is a priori unk ...

The diagnosis of sleep disorders is still often based on polysomnography, an in-lab exam allowing experts to perform accurate sleep staging, although this is labor-intensive, expensive, and exposing patients to unusual sleep conditions. A state-of-the-art ...

Deep neural networks (DNNs) are increasingly proposed as models of human vision, bolstered by their impressive performance on image classification and object recognition tasks. Yet, the extent to which DNNs capture fundamental aspects of human vision such ...

The use of meteorological radars to study snowfall microphysical properties and processes is well established, in particular via a few distinct techniques: the use of radar polarimetry, of multi-frequency radar measurements, and of the radar Doppler spectr ...

Intracranial hemorrhage (ICH) is a common finding in traumatic brain injury (TBI) and computed tomography (CT) is considered the gold standard for diagnosis. Automated detection of ICH provides clinical value in diagnostics and in the ability to feed robus ...

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

In this paper, we propose and compare personalized models for Productive Engagement (PE) recognition. PE is defined as the level of engagement that maximizes learning. Previously, in the context of robot-mediated collaborative learning, a framework of prod ...

We present a general framework for portfolio risk management in discrete time, based on a replicating martingale. This martingale is learned from a finite sample in a supervised setting. Our method learns the features necessary for an effective low-dimensi ...

Analog in-memory computing (AIMC) cores offers significant performance and energy benefits for neural network inference with respect to digital logic (e.g., CPUs). AIMCs accelerate matrix-vector multiplications, which dominate these applications’ run-time. ...

Background A variety of imaging methods are available to obtain kinematic data at an interface, with a widely varying range of spatial and temporal resolution. These methods require a trade-off between imaging rate and resolution. Objective A deep learning ...

In this paper, we propose a novel semi-supervised active salient object detection (SOD) method that actively acquires a small subset of the most discriminative and representative samples for labeling. Two main contributions have been made to prevent the me ...

The concerns for climate change and the transition to renewables is increasing the relevance of superconducting applications: High Temperature Superconductor (HTS) cables for efficient power transmission, superconducting magnets for nuclear fusion, superco ...

We consider the problem of enhancing user privacy in common data analysis and machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples from a generative adversarial network. We propose employing ...

We propose a novel machine learning (ML)-driven methodology to estimate biomechanical variables of interest traditionally obtained from upper-extremity musculoskeletal (MSK) modeling. MSK models facilitate personalized modeling, perform "what-if" analyses, ...

We present a search for galaxy-scale strong gravitational lenses in the initial 2500 square degrees of the Canada-France Imaging Survey (CFIS). We designed a convolutional neural network (CNN) committee that we applied to a selection of 2 344 002 r-band im ...

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data, and unsupervised settings pose many challenges, such as finding the right inductive bias in diverse scenarios. In this paper, we propose an object-centric mo ...

Theoretical and computational approaches to the study of materials and molecules have, over the last few decades, progressed at an exponential rate. Yet, the possibility of producing numerical predictions that are on par with experimental measurements is t ...

Deterministic equivalent and error universality of deep random features learning

Chattez avec Graph Search

Controlled learning of pointwise nonlinearities in neural-network-like architectures

Dependable learning and control through Neural ODEs

A Simple Framework for Open-Vocabulary Zero-Shot Segmentation

Multi-Agent Learning in Contextual Games under Unknown Constraints

PPG-Based Sleep Staging Using SleepPPGNet: Extension to Wearables, Improvements, Limitations

Divergences in color perception between deep neural networks and humans

Dual-frequency spectral radar retrieval of snowfall microphysics: a physics-driven deep-learning approach

Label-efficient deep semantic segmentation of intracranial hemorrhages in CT-scans

Text as a Richer Source of Supervision in Semantic Segmentation Tasks

Personalized Productive Engagement Recognition in Robot-Mediated Collaborative Learning

A machine learning approach to portfolio pricing and risk management for high-dimensional problems

ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning

High Resolution Interferometric Imaging of Liquid-Solid Interfaces with HOTNNET

Semi-supervised Active Salient Object Detection

A fibre optic and machine learning based health monitoring system for superconducting power applications in modern supergrids

Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees

Machine Learning for Musculoskeletal Modeling of Upper Extremity

Strong lensing in UNIONS: Toward a pipeline from discovery to modeling

Self-Supervision By Prediction For Object Discovery In Videos

Physics-enhanced machine learning with symmetry-adapted and long-range representations