Publications related to A Boolean Approach to Construct Neural Networks for Non-Boolean Problems

Training Distributed Neural Networks by Consensus

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

Reaction Enthalpies Using the Neural-Network-Based X1 Approach: The Important Choice of Input Descriptors

Matthew Wodrich

Artificial neural networks represent a simple but efficient way to model and correct known errors existing between commonly used density functional computations and experimental data. The recently proposed X1 approach combines B3LYP energies with a neural- ...

2009

Complex networks

Cécile Caretta Cartozo

The last decade has witnessed a fundamental change in the role of network theory. Side by side with the increasing relevance of interdisciplinarity, this ensemble of mathematical tools and methods has known such a success and such a wide range of different ...

EPFL2009

Combining Multiple Results of a Reverse Engineering Algorithm: Application to the DREAM Five Gene Network Challenge

Dario Floreano, Claudio Mattiussi, Daniel Marbach

The output of reverse engineering methods for biological networks is often not a single network prediction, but an ensemble of networks that are consistent with the experimentally measured data. In this paper, we consider the problem of combining the infor ...

Blackwell Publishing, 9600 Garsington Rd, Oxford Ox4 2Dq, Oxen, England2009

Evolvability of Neuromodulated Learning for Robots

Dario Floreano, Claudio Mattiussi, Peter Dürr, Andrea Soltoggio

Neuromodulation is thought to be one of the underlying principles of learning and memory in biological neural networks. Recent experiments have shown that neuroevolutionary methods benefit from neuromodulation in simple grid-world problems. In this paper w ...

IEEE Computer Society2008

An oscillatory neuromotor model of handwriting generation

A neuromotor model of handwritten stroke generation, in which stroke velocities are expressed as a Fourier-style decomposition of oscillatory neural activities, is presented. The neural network architecture consists of an input or stroke-selection layer, a ...

Springer Verlag2007

Artificial neural networks in spectrum fatigue life prediction of composite materials

Anastasios Vassilopoulos

An artificial neural network has been proved to be a sufficient tool for modelling fatigue life of multidirectional composite laminates made of GFRP composite materials and tested under constant amplitude loading patterns. Modelling efficiency of the netwo ...

Elsevier2007

On pooling networks and fluctuation in suboptimal detection framework

Cédric Duchene

Motivated by biological neural networks and distributed sensing networks, we study how pooling networks – or quantizers – with random thresholds can be used in detection tasks. We provide a brief overview of the use of deterministic quantizers in detection ...

2007

Fault-Tolerant Logic Gates Using Neuromorphic CMOS Circuits

Alexandre Schmid, Yusuf Leblebici, Neil Joye

Fault-tolerant design methods for VLSI circuits, which have traditionally been addressed at system level, will not be adequate for future very-deep submicron CMOS devices where serious degradation of reliability is expected. Therefore, a new design approac ...

IEEE2007

A Boolean Approach to Construct Neural Networks for Non-Boolean Problems

Graph Chatbot

Chat with Graph Search

Training Distributed Neural Networks by Consensus

Network Simplification: the Gaussian N-Relay Diamond Network

Reaction Enthalpies Using the Neural-Network-Based X1 Approach: The Important Choice of Input Descriptors

Complex networks

Combining Multiple Results of a Reverse Engineering Algorithm: Application to the DREAM Five Gene Network Challenge

Evolvability of Neuromodulated Learning for Robots

An oscillatory neuromotor model of handwriting generation

Artificial neural networks in spectrum fatigue life prediction of composite materials

On pooling networks and fluctuation in suboptimal detection framework

Fault-Tolerant Logic Gates Using Neuromorphic CMOS Circuits

Complex networks

Combining Multiple Results of a Reverse Engineering Algorithm: Application to the DREAM Five Gene Network Challenge

An oscillatory neuromotor model of handwriting generation

Training Distributed Neural Networks by Consensus

Reaction Enthalpies Using the Neural-Network-Based X1 Approach: The Important Choice of Input Descriptors

On pooling networks and fluctuation in suboptimal detection framework

Network Simplification: the Gaussian N-Relay Diamond Network

Artificial neural networks in spectrum fatigue life prediction of composite materials

Evolvability of Neuromodulated Learning for Robots

Fault-Tolerant Logic Gates Using Neuromorphic CMOS Circuits