Publications related to Nonlinear feature transformations for noise robust speech recognition

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

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 ...

EPFL2024

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Discrete choice modeling in the era of big data

Nicola Marco Ortelli

The technological advancements of the past decades have allowed transforming an increasing part of our daily actions and decisions into storable data, leading to a radical change in the scale and scope of available data in relation to virtually any object ...

EPFL2024

On the number of regions of piecewise linear neural networks

Michaël Unser, Alexis Marie Frederic Goujon

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

2024

Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection

Vinitra Swamy, Paola Mejia Domenzain, Julian Thomas Blackwell, Isadora Alves de Salles

Clustering in education, particularly in large-scale online environments like MOOCs, is essential for understanding and adapting to diverse student needs. However, the effectiveness of clustering depends on its interpretability, which becomes challenging w ...

2024

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Robust Data-Driven Controller Design with Finite Frequency Samples

Alireza Karimi, Philippe Louis Schuchert

Modern control synthesis methods rely on accurate models to derive a performant controller. Obtaining a good model is often a costly step, and has led to a renewed interest in data-driven synthesis methods. Frequency-response-based synthesis methods have b ...

2024

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

Philip Neil Garner

Auditory research aims in general to lead to understanding of physiological processes. By contrast, the state of the art in automatic speech processing (notably recognition) is dominated by large pre-trained models that are meant to be used as black-boxes. ...

2024

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

Jean-Paul Richard Kneib, Emma Elizabeth Tolley, Tianyue Chen, Michele Bianco

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 ...

Oxford Univ Press2024

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Alexander Carl Unnervik

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

EPFL2024

Nonlinear feature transformations for noise robust speech recognition

Graph Chatbot

Chat with Graph Search

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

Topics in statistical physics of high-dimensional machine learning

Discrete choice modeling in the era of big data

On the number of regions of piecewise linear neural networks

Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Robust Data-Driven Controller Design with Finite Frequency Samples

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

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

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

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

Topics in statistical physics of high-dimensional machine learning

Discrete choice modeling in the era of big data

Interpret3C: Interpretable Student Clustering Through Individualized Feature Selection

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Robust Data-Driven Controller Design with Finite Frequency Samples

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

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

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

On the number of regions of piecewise linear neural networks