Publications related to Theory of representation learning in cortical neural networks

The neural correlates of topographical disorientation-a lesion analysis study

Olaf Blanke, Lukas Heydrich, Eva Blondiaux

Topographical disorientation refers to the selective inability to orient oneself in familiar surroundings. However, to date its neural correlates remain poorly understood. Here we use quantitative lesion analysis and a lesion network mapping approach in or ...

Hoboken2024

Meta-learning to address diverse Earth observation problems across resolutions

Devis Tuia, Benjamin Alexander Kellenberger, Marc Conrad Russwurm

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 ...

London2024

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Nicolas Henri Bernard Flammarion, Hristo Georgiev Papazov, Scott William Pesme

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

2024

Butterfly effects in perceptual development: A review of the 'adaptive initial degradation' hypothesis

Lukas Vogelsang, Marin Vogelsang

Human perceptual development evolves in a stereotyped fashion, with initially limited perceptual capabilities maturing over the months or years following the commencement of sensory experience into robust proficiencies. This review focuses on the functiona ...

San Diego2024

Revisiting Character-level Adversarial Attacks for Language Models

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Yongtao Wu, Elias Abad Rocamora

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

2024

Machine Learning Security Against Data Poisoning: Are We There Yet?

Kathrin Grosse

Poisoning attacks compromise the training data utilized to train machine learning (ML) models, diminishing their overall performance, manipulating predictions on specific test samples, and implanting backdoors. This article thoughtfully explores these atta ...

Ieee Computer Soc2024

Deep Learning Generalization with Limited and Noisy Labels

Mahsa Forouzesh

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

EPFL2023

Supervised learning and inference of spiking neural networks with temporal coding

Ana Stanojevic

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 ...

EPFL2023

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Elisabetta Cornacchia

This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits.In the ...

EPFL2023

Probabilistic methods for neural combinatorial optimization

Nikolaos Karalias

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

EPFL2023

Theory of representation learning in cortical neural networks

Graph Chatbot

Chat with Graph Search

The neural correlates of topographical disorientation-a lesion analysis study

Meta-learning to address diverse Earth observation problems across resolutions

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Butterfly effects in perceptual development: A review of the 'adaptive initial degradation' hypothesis

Revisiting Character-level Adversarial Attacks for Language Models

Machine Learning Security Against Data Poisoning: Are We There Yet?

Deep Learning Generalization with Limited and Noisy Labels

Supervised learning and inference of spiking neural networks with temporal coding

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Probabilistic methods for neural combinatorial optimization

The neural correlates of topographical disorientation-a lesion analysis study

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Revisiting Character-level Adversarial Attacks for Language Models

Meta-learning to address diverse Earth observation problems across resolutions

Machine Learning Security Against Data Poisoning: Are We There Yet?

Deep Learning Generalization with Limited and Noisy Labels

Butterfly effects in perceptual development: A review of the 'adaptive initial degradation' hypothesis

Supervised learning and inference of spiking neural networks with temporal coding

Fundamental Limits in Statistical Learning Problems: Block Models and Neural Networks

Probabilistic methods for neural combinatorial optimization