Exponentially long orbits in Hopfield neural networks

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.

The advent of comprehensive synaptic wiring diagrams of large neural circuits has created the field of connectomics and given rise to a number of open research questions. One such question is whether it is possible to reconstruct the information stored in ...

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 ...

We propose a method for adapting neural networks to distribution shifts at test-time. In contrast to training-time robustness mechanisms that attempt to anticipate and counter the shift, we create a closed-loop system and make use of test-time feedback sig ...

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

The way biological brains carry out advanced yet extremely energy efficient signal processing remains both fascinating and unintelligible. It is known however that at least some areas of the brain perform fast and low-cost processing relying only on a smal ...

Deep neural networks trained on physical losses are emerging as promising surrogates for nonlinear numerical solvers. These tools can predict solutions to Maxwell's equations and compute gradients of output fields with respect to the material and geometric ...

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits. In th ...

According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...

While sensory representations in the brain depend on context, it remains unclear how such modulations are implemented at the biophysical level, and how processing layers further in the hierarchy can extract useful features for each possible contex-tual sta ...

We present LISA, a proof system and proof assistant for constructing proofs in schematic first-order logic and axiomatic set theory. The logical kernel of the system is a proof checker for first-order logic with equality and schematic predicate and fun ...

Current and future imaging surveys require photometric redshifts (photo-zs) to be estimated for millions of galaxies. Improving the photo-z quality is a major challenge but is needed to advance our understanding of cosmology. In this paper we explore how t ...

Over the course of a lifetime, the human brain acquires an astonishing amount of semantic knowledge and autobiographical memories, often with an imprinting strong enough to allow detailed information to be recalled many years after the initial learning exp ...

A hash proof system (HPS) is a form of implicit proof of membership to a language. Out of the very few existing post-quantum HPS, most are based on languages of ciphertexts of code-based or lattice-based cryptosystems and inherently suffer from a gap cause ...

The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

Computational models starting from large ensembles of evolutionarily related protein sequences capture a representation of protein families and learn constraints associated to protein structure and function. They thus open the possibility for generating no ...

This data set provides a computer-assisted proof for the kernel inequalities needed to prove universal optimality in the paper "Universal optimality of the E_8 and Leech lattices and interpolation formulas" (by Cohn, Kumar, Miller, Radchenko, and Viazovska ...

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 ...

To predict the response of masonry buildings to various types of loads, engineers use finite element models, specifically solid-element and macro-element models. For predicting masonry responses to seismic events in particular, equivalent frame models-a su ...

BackgroundIt is generally accepted that most evolutionary transformations at the phenotype level are associated either with rearrangements of genomic regulatory elements, which control the activity of gene networks, or with changes in the amino acid conten ...

Exponentially long orbits in Hopfield neural networks

Chat with Graph Search

Bayesian reconstruction of memories stored in neural networks from their connectivity

Optimizing Dynamic Aperture Studies with Active Learning

Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback

Deep Learning Generalization with Limited and Noisy Labels

Supervised learning and inference of spiking neural networks with temporal coding

Predicting nonlinear optical scattering with physics-driven neural networks

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Robust Training and Verification of Deep Neural Networks

NMDA-driven dendritic modulation enables multitask representation learning in hierarchical sensory processing pathways

LISA – A Modern Proof System

The PAU Survey and Euclid: Improving broadband photometric redshifts with multi-task learning star

A theory of memory consolidation and synaptic pruning in cortical circuits

A Gapless Post-quantum Hash Proof System in the Hamming Metric

Confidence Matters: Applications to Semantic Segmentation

Probabilistic methods for neural combinatorial optimization

Generative power of a protein language model trained on multiple sequence alignments

Computer-assisted proof of kernel inequalities

A new age in protein design empowered by deep learning

Automated image-based generation of finite element models for masonry buildings

Wide-scale identification of novel/eliminated genes responsible for evolutionary transformations