Statistical Physics of Computation Laboratory (SB)

Laboratory

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.

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 ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this an ...

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 ...

Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data silos. Sharing, transferring, and centralizing the data from silos, however, is difficult due to current privacy regulations (e.g., H ...

Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propose an ...

Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual represent ...

One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially-chosen perturbations of data. Despite the promi ...

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...

Intelligent Fault Diagnosis (IFD) based on deep learning has proven to be an effective and flexible solution, attracting extensive research. Deep neural networks can learn rich representations from vast amounts of representative labeled data for various ap ...

We present a statistical framework to benchmark the performance of reconstruction algorithms for linear inverse problems, in particular, neural-network-based methods that require large quantities of training data. We generate synthetic signals as realizati ...

Statistical Physics of Computation Laboratory (SB)

Chat with Graph Search

Robust Training and Verification of Deep Neural Networks

Transformer Models for Vision

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Predicting nonlinear optical scattering with physics-driven neural networks

Privacy-preserving federated neural network training and inference

An exact mapping from ReLU networks to spiking neural networks

BLACK-BOX ATTACKS ON IMAGE ACTIVITY PREDICTION AND ITS NATURAL LANGUAGE EXPLANATIONS

Adversarial Training Should Be Cast As a Non-Zero-Sum Game

Benign Overfitting in Deep Neural Networks under Lazy Training

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis

A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods