Information, Learning & Physics Laboratory (STI/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.

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 ...

Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient calibration methods for neural networks is therefore an important endeavour tow ...

Effective properties of materials with random heterogeneous structures are typically determined by homogenising the mechanical quantity of interest in a window of observation. The entire problem setting encompasses the solution of a local PDE and some aver ...

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 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 ...

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 ...

Touchscreens are nowadays the preferred choice for user interfaces in consumer electronics. Significant technological advances have been made in terms of touch sensing and visual quality. However, the haptic feedback offered by commercial products is still ...

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 ...

Humans and animals constantly adapt to their environment over the course of their life. This thesis seeks to integrate various timescales of adaptation, ranging from the adaptation of synaptic connections between spiking neurons (milliseconds), rapid behav ...

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 ...

Information, Learning & Physics Laboratory (STI/SB)

Chat with Graph Search

Privacy-preserving federated neural network training and inference

Expectation consistency for calibration of neural networks

DeepBND: A machine learning approach to enhance multiscale solid mechanics

Supervised learning and inference of spiking neural networks with temporal coding

An exact mapping from ReLU networks to spiking neural networks

Benign Overfitting in Deep Neural Networks under Lazy Training

Deep Learning for Localized-Haptic Feedback in Tactile Surfaces

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis

From event-based surprise to lifelong learning. A journey in the timescales of adaptation

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