Publications related to Improving Object Classification using Pose Information

Deep Learning Theory Through the Lens of Diagonal Linear Networks

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

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Alexander Mathis, Alberto Silvio Chiappa, Alessandro Marin Vargas, Axel Bisi

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

EPFL Infoscience2024

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

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

Penalising the biases in norm regularisation enforces sparsity

Nicolas Henri Bernard Flammarion, Etienne Patrice Boursier

Controlling the parameters' norm often yields good generalisation when training neural networks. Beyond simple intuitions, the relation between parameters' norm and obtained estimators theoretically remains misunderstood. For one hidden ReLU layer networks ...

2023

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Angelos Katharopoulos

Deep neural networks have completely revolutionized the field of machinelearning by achieving state-of-the-art results on various tasks ranging fromcomputer vision to protein folding. However, their application is hindered bytheir large computational and m ...

EPFL2022

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu, Yongtao Wu

Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural network architectures, but it is incomplete for neural networks with Hadamar ...

2022

ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning

David Atienza Alonso, Marina Zapater Sancho, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Irem Boybat Kara, Yasir Mahmood Qureshi, Joshua Alexander Harrison Klein, Abu Sebastian

Analog in-memory computing (AIMC) cores offers significant performance and energy benefits for neural network inference with respect to digital logic (e.g., CPUs). AIMCs accelerate matrix-vector multiplications, which dominate these applications’ run-time. ...

2022

Biologically plausible unsupervised learning in shallow and deep neural networks

Bernd Albert Illing

The way our brain learns to disentangle complex signals into unambiguous concepts is fascinating but remains largely unknown. There is evidence, however, that hierarchical neural representations play a key role in the cortex. This thesis investigates biolo ...

EPFL2021

Loss landscape and symmetries in Neural Networks

Mario Geiger

Neural networks (NNs) have been very successful in a variety of tasks ranging from machine translation to image classification. Despite their success, the reasons for their performance are still not well-understood. This thesis explores two main themes: lo ...

EPFL2021

Improving Object Classification using Pose Information

Graph Chatbot

Chat with Graph Search

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Deep Learning Generalization with Limited and Noisy Labels

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

Penalising the biases in norm regularisation enforces sparsity

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning

Biologically plausible unsupervised learning in shallow and deep neural networks

Loss landscape and symmetries in Neural Networks

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Deep Learning Generalization with Limited and Noisy Labels

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

Biologically plausible unsupervised learning in shallow and deep neural networks

ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning

Penalising the biases in norm regularisation enforces sparsity

Stop Wasting my FLOPS: Improving the Efficiency of Deep Learning Models

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Loss landscape and symmetries in Neural Networks