Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks

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.

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Animals have to navigate complex environments and perform intricate swimming maneuvers in the real world. To conquer these challenges, animals evolved a variety of motion control strategies. While it is known that many factors contribute to motion control, ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and computational hard ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

In recent years, neural quantum states have emerged as a powerful variational approach, achieving state-of-the-art accuracy when representing the ground-state wave function of a great variety of quantum many-body systems, including spin lattices, interacti ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks

Chattez avec Graph Search

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Improving the accuracy and interpretability of neural networks for wind power forecasting

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Using deep reinforcement learning to investigate stretch feedback during swimming of the lamprey

Random matrix methods for high-dimensional machine learning models

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

Learning to Assemble with Alternative Plans

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Topics in statistical physics of high-dimensional machine learning

Training hybrid neural networks with multimode optical nonlinearities using digital twins

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Accurate neural quantum states for interacting lattice bosons

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Machine Learning for Modeling Stock Returns

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology