The committee machine: computational to statistical gaps in learning a two-layers neural network

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.

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

The International Tokamak Physics Activity (ITPA) has developed a comprehensive overview of the results of its coordinated R&D activities in fusion physics and diagnostics implemented during the past two decades with the aim of developing an improved physi ...

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, ...

Estimating ecosystem-atmosphere fluxes such as evapotranspiration (ET) in a robust manner and at a global scale remains a challenge. Methods based on machine learning (ML) have shown promising results in achieving such upscaling, providing a complementary ...

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving differential equations by integrating physical laws into the learning process. This work leverages PINNs to simulate gravitational collapse, a critical phenomenon in astro ...

Recently, cutting-edge brain-machine interfaces (BMIs) have revealed the potential of decoders such as recurrent neural networks (RNNs) in predicting attempted handwriting [1] or speech [2], enabling rapid communication recovery after paralysis. However, c ...

Integer linear programming (ILP) is an elegant approach to solve linear optimization problems, naturally described using integer decision variables. Within the context of physics-inspired machine learning (ML) applied to chemistry, we demonstrate the relev ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

The digitization of 3D deformable objects remains a significant challenge in computer graphics and vision, particularly in the accurate modeling of garments. Garments exhibit complex shape variability, non-rigid deformations, and frequent self-occlusion, m ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

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 ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

Topographical disorientation refers to the selective inability to orient oneself in familiar surroundings. However, to date its neural correlates remain poorly understood. Here we use quantitative lesion analysis and a lesion network mapping approach in or ...

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 ...

Translation elongation plays an important role in regulating protein concentrations in the cell, and dysregulation of this process has been linked to several human diseases. In this study, we use data from ribo-seq experiments to model ribosome densities, ...

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

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 ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

The committee machine: computational to statistical gaps in learning a two-layers neural network

Chat with Graph Search

On the number of regions of piecewise linear neural networks

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Introduction and Overview: Chapter 1 of the Special Issue: on the Path to Tokamak Burning Plasma Operation

Machine Learning for Modeling Stock Returns

On the added value of sequential deep learning for the upscaling of evapotranspiration

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

SPINN: Advancing Cosmological Simulations of Fuzzy Dark Matter with Physics Informed Neural Networks

33.3 MiBMI: A 192/512-Channel 2.46mm² Miniaturized Brain-Machine Interface Chipset Enabling 31-Class Brain-to-Text Conversion Through Distinctive Neural Codes

Integer Linear Programming for Unsupervised Training Set Selection in Molecular Machine Learning

Enabling Uncertainty Estimation in Iterative Neural Networks

Neural Garment Modeling

Partial discharge localization in power transformer tanks using machine learning methods

Optimizing Dynamic Aperture Studies with Active Learning

Robust machine learning for neuroscientific inference

The neural correlates of topographical disorientation-a lesion analysis study

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

Towards improving full-length ribosome density prediction by bridging sequence and graph-based representations

Gibbs sampling the posterior of neural networks

Random matrix methods for high-dimensional machine learning models

Incorporating Projective Geometry into Deep Learning