The physics of energy-based models

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.

Computational Imaging (CI) is the field concerned with reconstructing images of some quantity of interest from a finite number of measurements. It is pervasive in science and engineering problems by enabling the reconstruction of images from a variety of m ...

The rapid progress in the field of deep learning has had a significant impact on protein design. Deep learning methods have recently produced a breakthrough in protein structure prediction, leading to the availability of high-quality models for millions of ...

Critical quantum systems are a promising resource for quantum metrology applications, due to the diverging susceptibility developed in proximity of phase transitions. Here, we assess the metrological power of parametric Kerr resonators undergoing driven-di ...

This paper investigates the potential impact of deep generative models on the work of creative professionals, specifically focusing on fashion design. We argue that current generative modeling tools lack critical features that would make them useful creati ...

Over the past decade, interatomic potentials based on machine learning (ML) techniques have become an indispensable tool in the atomic-scale modeling of materials. Trained on energies and forces obtained from electronic-structure calculations, they inherit ...

Deep Neural Networks (DNNs) have achieved great success in a wide range of applications, such as image recognition, object detection, and semantic segmentation. Even though the discriminative power of DNNs is nowadays unquestionable, serious concerns have ...

Signal recovery under generative neural network priors has emerged as a promising direction in statistical inference and computational imaging. Theoretical analysis of reconstruction algorithms under generative priors is, however, challenging. For generati ...

Implicit neural representations (INRs) have recently emerged as a promising alternative to classical discretized representations of signals. Nevertheless, despite their practical success, we still do not understand how INRs represent signals. We propose a ...

The automatic recognition of food on images has numerous interesting applications, including nutritional tracking in medical cohorts. The problem has received significant research attention, but an ongoing public benchmark on non-biased (i.e., not scraped ...

Codebook-based optimizations are a class of algorithmic-level transformations able to effectively reduce the computing and memory requirements of Convolutional Neural Networks (CNNs). This approach tightly limits the number of unique weights in each layer, ...

The W boson mass is measured using proton-proton collision data at root s = 13 TeV corresponding to an integrated luminosity of 1.7fb(-1) recorded during 2016 by the LHCb experiment. With a simultaneous fit of the muon q/p(T) distribution of a sample of W ...

We consider the problem of sampling from a density of the form p(x) ? exp(-f (x) - g(x)), where f : Rd-+ R is a smooth function and g : R-d-+ R is a convex and Lipschitz function. We propose a new algorithm based on the Metropolis-Hastings framework. Under ...

Despite governing heat management in any realistic device, the microscopic mechanisms of heat transport in all-solid-state electrolytes are poorly known: existing calculations, all based on simplistic semi-empirical models, are unreliable for superionic co ...

In situ, two-dimensional (2D) Langmuir probe measurements across a large part of the TCV outer divertor are reported in L-mode discharges with and without divertor baffles. This provides detailed insights into time averaged profiles, particle fluxes, and f ...

A device capable of converting single quanta of the microwave field to the optical domain is an outstanding endeavor in the context of quantum interconnects between distant superconducting qubits, but likewise can have applications in other fields, such as ...

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods learn representations that cannot be interpreted in a straightforward way and that are relat ...

The physics of energy-based models

Chat with Graph Search

Computational Imaging: a Multi-Facet Perspective

A new age in protein design empowered by deep learning

Critical parametric quantum sensing

Fashioning the Future: Unlocking the Creative Potential of Deep Generative Models for Design Space Exploration

Beyond potentials: Integrated machine learning models for materials

Understanding Deep Neural Networks using Adversarial Attacks

Multi-layer State Evolution Under Random Convolutional Design

A Structured Dictionary Perspective on Implicit Neural Representations

The Food Recognition Benchmark: Using Deep Learning to Recognize Food in Images

An Accuracy-Driven Compression Methodology to Derive Efficient Codebook-Based CNNs

Measurement of the W boson mass

An Efficient Sampling Algorithm for Non-smooth Composite Potentials

Temperature- and vacancy-concentration-dependence of heat transport in Li3ClO from multi-method numerical simulations

New insights on divertor parallel flows,E x B drifts, and fluctuations from in situ, two-dimensional probe measurement in the Tokamak a Configuration Variable

Quantum coherent microwave-optical transduction using high-overtone bulk acoustic resonances

node2coords: Graph Representation Learning with Wasserstein Barycenters