Deep Boltzmann Machines: Rigorous Results at Arbitrary Depth

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.

We initiate the study of neural network quantum state algorithms for analyzing continuous-variable quantum systems in which the quantum degrees of freedom correspond to coordinates on a smooth manifold. A simple family of continuous-variable trial wavefunc ...

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

In this thesis we address various factors that contribute both theoretically and practically to mitigating supply demand mismatches. The thesis is composed of three chapters, where each chapter is an independent scientific paper. In the first paper, we dev ...

A device (1) and method for processing data comprises at least one input layer (2), at least one modulation layer (3), and at least one output layer (4). The input layer (2) is configured to receive at least one carrier signal (Sc). The modulation layer (3 ...

We describe a novel method to compute the components of dynamo tensors from direct magnetohydrodynamic (MHD) simulations. Our method relies upon an extension and generalization of the standard H & ouml;gbom CLEAN algorithm widely used in radio astronomy to ...

A major upgrade of the European DIPOle (EDIPO) test facility, which will allow the testing of superconducting samples both for fusion and for high-energy physics applications, is taking place at the Swiss Plasma Center. With a target background field of 15 ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

Measuring bathymetry has always been a major scientific and technological challenge. In this work, we used a deep learning technique for inferring bathymetry from the depth-averaged velocity field. The training of the neural network is based on 5742 labora ...

Reducing the computational time required by high-fidelity, full-order models (FOMs) for the solution of problems in cardiac mechanics is crucial to allow the translation of patient-specific simulations into clinical practice. Indeed, while FOMs, such as th ...

We study the limit behaviour of sequences of non-convex, vectorial, random integral functionals, defined on W1,1, whose integrands are ergodic and satisfy degenerate linear growth conditions. The latter involve suitable random, scale-dependent weight-funct ...

Linear-Quadratic-Gaussian (LQG) control is a fundamental control paradigm that is studied in various fields such as engineering, computer science, economics, and neuroscience. It involves controlling a system with linear dynamics and imperfect observations ...

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 ...

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 ...

This thesis is situated at the crossroads between machine learning and control engineering. Our contributions are both theoretical, through proposing a new uncertainty quantification methodology in a kernelized context; and experimental, through investigat ...

Forecasting is a capability inherent in humans when navigating. Humans routinely plan their paths, considering the potential future movements of those around them. Similarly, to achieve comparable sophistication and safety, autonomous systems must embrace ...

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

When spatially shared among multiple tenants, field-programmable gate arrays (FPGAs) are vulnerable to remote power side-channel analysis attacks. Using carefully crafted on-chip voltage sensors, adversaries can extract secrets (e.g., encryption keys or th ...

To build biophysically detailed models of brain cells, circuits, and regions, a data-driven approach is increasingly being adopted. This helps to obtain a simulated activity that reproduces the experimentally recorded neural dynamics as faithfully as possi ...

Deep Boltzmann Machines: Rigorous Results at Arbitrary Depth

Chat with Graph Search

Continuous-variable neural network quantum states and the quantum rotor model

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Optimizing Sales Forecasting, Inventory, Pricing and Sourcing Decisions

Optical data processing using structural non-linearity

Iterative removal of sources to model the turbulent electromotive force

Progress in the design and manufacturing of the EDIPO 2 cryostat

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Universal and adaptive methods for robust stochastic optimization

Bed Topography Inference from Velocity Field Using Deep Learning

Efficient approximation of cardiac mechanics through reduced-order modeling with deep learning-based operator approximation

Stochastic homogenization of degenerate integral functionals with linear growth

Distributionally Robust Linear Quadratic Control

Robust Training and Verification of Deep Neural Networks

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

Machine Learning Methods for Robust Uncertainty Quantification and Controller Approximation

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Robust Collaborative Learning with Linear Gradient Overhead

Active Wire Fences for Multitenant FPGAs

Online interoperable resources for building hippocampal neuron models via the Hippocampus Hub