Publications associées à Capacity of Deterministic Z-Chain Relay-Interference Network

Layer-Wise Learning Framework for Efficient DNN Deployment in Biomedical Wearable Systems

David Atienza Alonso, Amir Aminifar, Saleh Baghersalimi, Tomas Teijeiro Campo, Alireza Amirshahi

The development of low-power wearable systems requires specialized techniques to accommodate their unique requirements and constraints. While significant advancements have been made in the inference phase of artificial intelligence, the training phase rema ...

2023

Annealing and Replica-Symmetry in Deep Boltzmann Machines

Emanuele Mingione, Diego Alberici

In this paper we study the properties of the quenched pressure of a multi-layer spin-glass model (a deep Boltzmann Machine in artificial intelligence jargon) whose pairwise interactions are allowed between spins lying in adjacent layers and not inside the ...

SPRINGER2020

Private and Secure Distributed Learning

Georgios Damaskinos

The ever-growing number of edge devices (e.g., smartphones) and the exploding volume of sensitive data they produce, call for distributed machine learning techniques that are privacy-preserving. Given the increasing computing capabilities of modern edge de ...

EPFL2020

AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks

Sabine Süsstrunk, Frederike Dümbgen, Majed El Helou

The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can be expensive and time-consuming to collect. A common practical approach to attenuate overfitting i ...

IEEE2020

DermoNet: densely linked convolutional neural network for efficient skin lesion segmentation

Jean-Philippe Thiran, Saleh Baghersalimi, Hazim Kemal Ekenel

Recent state-of-the-art methods for skin lesion segmentation are based on convolutional neural networks (CNNs). Even though these CNN-based segmentation approaches are accurate, they are computationally expensive. In this paper, we address this problem and ...

2019

Entropy and mutual information in models of deep neural networks

Nicolas Macris, Jean François Emmanuel Barbier, Clément Dominique Luneau, Florent Gérard Krzakala, Lenka Zdeborová

We examine a class of stochastic deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) we show how entropies and mutual informations can be derived from heuristic statistical physics ...

2019

Capsule networks, but not convolutional networks explain global configurational visual effects

Michael Herzog, Alban Bornet, Adrien Christophe Doerig

In human vision, perception of local features depends on all elements in the visual field and their exact configuration. For example, observers performed a vernier discrimination task. When a surrounding square was added to the vernier, the task became muc ...

2019

Deep Micro-Dictionary Learning and Coding Network

Yan Yan, Wei Wang, Wei Xiao

In this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN). DDLCN has most of the standard deep learning layers (pooling, fully, connected, input/output, etc.) but the main difference is that the fundamental convolutional l ...

IEEE2019

Entropy and mutual information in models of deep neural networks

Nicolas Macris, Jean François Emmanuel Barbier, Clément Dominique Luneau, Florent Gérard Krzakala, Lenka Zdeborová

We examine a class of stochastic deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical physics ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018

EMPoWER Hybrid Networks: Exploiting Multiple Paths over Wireless and ElectRical Mediums

Patrick Thiran, Julien Pierre Sacha Herzen, Christina Vlachou, Sébastien Christophe Henri

Several technologies, such as WiFi, Ethernet and power-line communications (PLC), can be used to build residential and enterprise networks. These technologies often co-exist; most networks use WiFi, and buildings are readily equipped with electrical wires ...

2016

When Neurons Fail - Technical Report

Rachid Guerraoui, El Mahdi El Mhamdi

Neural networks have been traditionally considered robust in the sense that their precision degrades gracefully with the failure of neurons and can be compensated by additional learning phases. Nevertheless, critical applications for which neural networks ...

EPFL2016

On Multi-Dimensional Privacy in Context-Aware Mobile Networks

Igor Bilogrevic

By the end of 2013, the number of internet-connected mobile devices is expected to exceed that of humans. Omnipresent and context-aware, mobile devices enable people to communicate and exchange data anytime and almost anywhere. The myriad of ”digital footp ...

EPFL2014

Multiple task learning in recurrent neural networks using layered reservoirs

Martin Hasler, Mahdi Jalili, Ali Ajdari Rad

In this paper, to learn multiple tasks sharing same inputs, a two-layer architecture for a reservoir based recurrent neural network is proposed. The inputs are fed into the general workspace layer where the weights are adapted to provide maximum informatio ...

2009

Interference management in impulse-radio ultra-wide band networks

Ruben Merz

We consider networks of impulse-radio ultra-wide band (IR-UWB) devices. We are interested in the architecture, design, and performance evaluation of these networks in a low data-rate, self-organized, and multi-hop setting. IR-UWB is a potential physical la ...

EPFL2008

Distributed and Component Oriented Tools for Communication Networks Using Web Services

Christian Gaumier, Sébastien Rumley, Christophe Trefois

Modern communication networks are reaching a high level of complexity. As their global dimensioning and performance evaluation are very hard tasks, a multi-layer approach is generally applied to divide them in smaller problems easier to tackle. Within this ...

ARGESIM2007

Layered Complex Networks

Patrick Thiran, Maciej Kurant

Many complex networks are only a part of larger systems, where a number of coexisting topologies interact and depend on each other. We introduce a layered model to facilitate the description and analysis of such systems. As an example of its application, w ...

2006