A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs

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.

Atomistic machine learning has revolutionized atomistic modeling. Traditionally, molecular dynamics simulations relied on classical force fields or electronic structure calculations like Density Functional Theory. Classical force fields are fast but less p ...

Federated Learning (FL) enables end-user devices to collaboratively train ML models without sharing raw data, thereby preserving data privacy. In FL, a central parameter server coordinates the learning process by iteratively aggregating the trained models ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high gen ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Traditional example-based learning methods are often limited by static, expert-created content. Hence, they face challenges in scalability, engagement, and effectiveness, as some learners might struggle to relate to the examples or find them relevant. To a ...

We address the problem of denoising data from a Gaussian mixture using a twolayer non-linear autoencoder with tied weights and a skip connection. We consider the high-dimensional limit where the number of training samples and the input dimension jointly te ...

Compute memories are memory arrays augmented with dedicated logic to support arithmetic. They support the efficient execution of data-centric computing patterns, such as those characterizing Artificial Intelligence (AI) algorithms. These architectures can ...

A search is performed for narrow resonances decaying to final states of two jets, with at least one jet ffiffioriginating from a b quark, in proton-proton collisions at p s = 13 TeV. The data set corresponds to an integrated luminosity of 138 fb-1 collecte ...

It was recently shown that almost all solutions in the symmetric binary perceptron are isolated, even at low constraint densities, suggesting that finding typical solutions is hard. In contrast, some algorithms have been shown empirically to succeed in fin ...

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the b ...

We address the problem of designing stabilizing control policies for nonlinear systems in discrete-time, while minimizing an arbitrary cost function. When the system is linear and the cost is convex, the System Level Synthesis (SLS) approach offers an effe ...

Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such as distributed SGD, in a way that guarantees convergence despite the presence ...

Training deep neural networks (DNNs) can be difficult due to the occurrence of vanishing/explod- ing gradients during weight optimization. To avoid this problem, we propose a class of DNNs stemming from the time discretization of Hamiltonian systems. The t ...

Air traffic management and specifically air-traffic control (ATC) rely mostly on voice communications between Air Traffic Controllers (ATCos) and pilots. In most cases, these voice communications follow a well-defined grammar that could be leveraged in Aut ...

In the literature, the task of dysarthric speech intelligibility assessment has been approached through development of different low-level feature representations, subspace modeling, phone confidence estimation or measurement of automatic speech recognitio ...

The impact of stressful events is especially important during early life, because certain cortical regions, especially the prefrontal cortex (PFC), are still developing. Consequently, aversive experiences that occur during the peripubertal period can cause ...

A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs

Chattez avec Graph Search

Advancing understanding and practical performance of machine learning interatomic potentials

Practical Federated Learning without a Server

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

GELEX: Generative AI-Hybrid System for Example-Based Learning

High-dimensional Asymptotics of Denoising Autoencoders

Overflow-free Compute Memories for Edge AI Acceleration

Search for narrow resonances in the b-tagged dijet mass spectrum in proton-proton collisions at √s=13 TeV

Binary Perceptron: Efficient Algorithms Can Find Solutions in a RareWell-Connected Cluster

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss

Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systems

Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums

A unified framework for Hamiltonian deep neural networks

Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems

Utterance Verification-Based Dysarthric Speech Intelligibility Assessment Using Phonetic Posterior Features

Long term effects of peripubertal stress on excitatory and inhibitory circuits in the prefrontal cortex of male and female mice