Safe Deep 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.

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Animals have to navigate complex environments and perform intricate swimming maneuvers in the real world. To conquer these challenges, animals evolved a variety of motion control strategies. While it is known that many factors contribute to motion control, ...

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and computational hard ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

In recent years, neural quantum states have emerged as a powerful variational approach, achieving state-of-the-art accuracy when representing the ground-state wave function of a great variety of quantum many-body systems, including spin lattices, interacti ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

Sign Language conveys information through multiple channels composed of manual (handshape, hand movement) and non-manual (facial expression, mouthing, body posture) components. Sign language assessment involves giving granular feedback to a learner, in ter ...

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

Neurons in the human amygdala and hippocampus are classically thought to encode a person’s identity invariant to visual features. However, it remains largely unknown how visual information from higher visual cortical areas is translated into such a semanti ...

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

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 ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

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 ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

The work presented in this thesis lies at the intersection of Machine Learning (ML) and control theory. The first part is dedicated to the design of Deep Neural Network (DNN) architectures with specific numerical properties, inspired by dynamical systems m ...

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 ...

Safe Deep Neural Networks

Chat with Graph Search

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Improving the accuracy and interpretability of neural networks for wind power forecasting

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Using deep reinforcement learning to investigate stretch feedback during swimming of the lamprey

Learning to Assemble with Alternative Plans

Training hybrid neural networks with multimode optical nonlinearities using digital twins

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

Accurate neural quantum states for interacting lattice bosons

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Posterior-Based Analysis of Spatio-Temporal Features for Sign Language Assessment

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Feature-based encoding of face identity by single neurons in the human amygdala and hippocampus

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Domain shift, domain adaptation, and generalization: A focus on MRI

Incorporating Projective Geometry into Deep Learning

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Optimizing Dynamic Aperture Studies with Active Learning

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Navigating the Loop: From Control Systems to Neural Networks and Back

Robust machine learning for neuroscientific inference