Understanding generalization and robustness in modern deep learning

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.

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

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 ...

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

As a data-driven approach, multi-agent reinforcement learning (MARL) has made remarkable advances in solving cooperative residential load scheduling problems. However, centralized training, the most common paradigm for MARL, limits large-scale deployment i ...

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

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 ...

We study the generalization of iterative noisy gradient schemes on smooth non-convex losses. Formally, we establish time-independent information theoretic generalization bounds for Stochastic Gradient Langevin Dynamics (SGLD) that do not diverge as the ite ...

We develop a model-free approach to optimally control stochastic, Markovian systems subject to a reach-avoid constraint. Specifically, the state trajectory must remain within a safe set while reaching a target set within a finite time horizon. Due to the t ...

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 ...

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless, when performing ...

Designing novel materials is greatly dependent on understanding the design principles, physical mechanisms, and modeling methods of material microstructures, requiring experienced designers with expertise and several rounds of trial and error. Although rec ...

When a plasma disrupts in a tokamak, significant heat and electromagnetic loads are deposited onto the surrounding device components. These forces scale with plasma current and magnetic field strength, making disruptions one of the key challenges for futur ...

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 capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

What changes with age? Results in reinforcement learning (RL) are mixed. Some studies found deteriorated RL performance in older participants compared to younger controls whereas other studies did not. Daniel et al. (J Neurosci 40(5):1084–1096, 2020. 10.15 ...

Understanding generalization and robustness in modern deep learning

Chat with Graph Search

A comparative analysis of gene expression profiling by statistical and machine learning approaches

Predicting the long-term collective behaviour of fish pairs with deep learning

Person Re-Identification and its Application to Multi-Object Tracking

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

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Meta-learning to address diverse Earth observation problems across resolutions

Scalable Multi-agent Reinforcement Learning for Residential Load Scheduling Under Data Governance

Residual-based attention in physics-informed neural networks

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Generalization of Noisy SGD in Unbounded Non-convex Settings

A learning-based approach to stochastic optimal control under reach-avoid constraint

Incorporating Projective Geometry into Deep Learning

LIONHEART: A Layer-based Mapping Framework for Heterogeneous Systems with Analog In-Memory Computing Tiles

Text-to-Microstructure Generation Using Generative Deep Learning

Plasma state monitoring and disruption characterization using multimodal VAEs

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

Safe Deep Neural Networks

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Intact reinforcement learning in healthy ageing