Publications related to Towards Commoditizing Simulations of System Models Using Recurrent Neural Networks

Full-Pulse Tomographic Reconstruction with Deep Neural Networks

Olivier Sauter, Ambrogio Fasoli, Basil Duval, Stefano Coda, Jonathan Graves, Yves Martin, Duccio Testa, Patrick Blanchard, Alessandro Pau, Cristian Sommariva, Henri Weisen, Richard Pitts, Yann Camenen, Jan Horacek, Javier García Hernández, Marco Wischmeier, Nicola Vianello, Mikhail Maslov, Federico Nespoli, Yao Zhou, David Pfefferlé, Davide Galassi, Antonio José Pereira de Figueiredo, Jonathan Marc Philippe Faustin, Liang Yao, Dalziel Joseph Wilson, Hamish William Patten, Samuel Lanthaler, Bernhard Sieglin, Otto Asunta

Plasma tomography consists of reconstructing a two-dimensional radiation profile of a poloidal cross section of a fusion device based on line-integrated measurements along several lines of sight. The reconstruction process is computationally intensive, and ...

2018

Entropy and mutual information in models of deep neural networks

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

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

Training Distributed Neural Networks by Consensus

Martin Hasler, Leonidas Georgopoulos

We address the problem of learning a classifier from distributed data over a number of arbitrarily connected machines without exchange of the datapoints. Our purpose is to train a neural network at each machine as if the entire dataset was locally availabl ...

2011

Network Simplification: the Gaussian N-Relay Diamond Network

Christina Fragouli, Ayfer Özgür Aydin

We consider the Gaussian

N

-relay diamond network, where a source wants to communicate to a destination through a layer of

N

-relay nodes. We investigate the following question: What fraction of the capacity can we maintain by using only

k

out of the $ ...

2010

Fast Face Detection using MLP and FFT

We propose a new technique for a faster computation of the activities of the hidden layer units. This has been demonstrated on face detection examples. ...

1999

An Optical Thresholding Perceptron

An implementation of an optical perceptron with a soft optical threshold trained with an adapted BP algorithm is described as a precursor to an optical multilayer perceptron (MLP). It has 64 inputs and ten outputs. The soft threshold is implemented by a li ...

1997

An Optical Thresholding Perceptron

An implementation of an optical perceptron with a soft optical threshold trained with an adapted BP algorithm is described as a precursor to an optical multilayer perceptron (MLP). It has 64 inputs and ten outputs. The soft threshold is implemented by a li ...

IDIAP1997

Connectionist Quantization Functions

One of the main strengths of connectionist systems, also known as neural networks, is their massive parallelism. However, most neural networks are simulated on serial computers where the advantage of massive parallelism is lost. For large and real-world ap ...

1996

Design and analysis of a systolic array for neural computation

Research on artificial neural networks (ANNs) has been carried out for more than five decades. A renewed interest appeared in the 80's with the finding of powerful models like J. Hopfield's recurrent networks, T. Kohonen's self-organizing feature maps, and ...

EPFL1994

Towards Commoditizing Simulations of System Models Using Recurrent Neural Networks

Graph Chatbot

Chat with Graph Search

Full-Pulse Tomographic Reconstruction with Deep Neural Networks

Entropy and mutual information in models of deep neural networks

Training Distributed Neural Networks by Consensus

Network Simplification: the Gaussian N-Relay Diamond Network

Fast Face Detection using MLP and FFT

An Optical Thresholding Perceptron

An Optical Thresholding Perceptron

Connectionist Quantization Functions

Design and analysis of a systolic array for neural computation

Design and analysis of a systolic array for neural computation

An Optical Thresholding Perceptron

Fast Face Detection using MLP and FFT

Connectionist Quantization Functions

Entropy and mutual information in models of deep neural networks

Training Distributed Neural Networks by Consensus

An Optical Thresholding Perceptron

Network Simplification: the Gaussian N-Relay Diamond Network

Full-Pulse Tomographic Reconstruction with Deep Neural Networks