Martin Hasler

Publications associées (53)

À propos
Confidentialité
Mentions légales

Graph Chatbot

Automatic skill acquisition in Reinforcement Learning using connection graph stability centrality

Martin Hasler, Ali Ajdari Rad

Reinforcement Learning (RL) is an approach for training agent's behavior through trial-and-error interactions with a dynamic environment. An important problem of RL is that in large domains an enormous number of decisions are to be made. Hence, instead of ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2010

Community detection enhancement in networks using proper weighting and partial synchronization

Martin Hasler, Ali Ajdari Rad, Alireza Khadivi

A community in a network is a subset of vertices densely connected to each other, but less connected to the vertices outside. Many different approaches have been developed to find such structures in a given network, but the main drawback of most of the ava ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2010

Reservoir optimization in recurrent neural networks using properties of Kronecker product

Martin Hasler, Ali Ajdari Rad, Mahdi Jalili

Recurrent neural networks based on reservoir computing are increasingly being used in many applications. Optimization of the topological structure of the reservoir and the internal connection weights for a given task is one of the most important problems i ...

2010

Topography of EEG multivariate phase synchronization in early Alzheimer's disease

Martin Hasler, Reto Meuli, Mahdi Jalili

Alzheimer's disease (AD) is likely to disrupt the synchronization of the bioelectrical processes in the distributed cortical networks underlying cognition. We analyze the surface topography of the multivariate phase synchronization (MPS) of multichannel EE ...

2010

Fire Detection and Localization Using Wireless Sensor Networks

Martin Hasler, Alireza Khadivi

A Wireless Sensor Network (WSN) is a network of usually a large number of small sensor nodes that are wirelessly connected to each other in order to remotely monitor an environment or phenomena. Sensor nodes use the data aggregation method as an effective ...

Springer, 233 Spring Street, New York, Ny 10013, United States2010

Attenuated asymmetry of functional connectivity in schizophrenia: A high-resolution EEG study

Martin Hasler, Mahdi Jalili, Kim Do, Reto Meuli

The interhemispheric asymmetries that originate from connectivity-related structuring of the cortex are compromised in schizophrenia (SZ). Under the assumption that such abnormalities affect functional connectivity, we analyzed its correlate-EEG synchroniz ...

Wiley-Blackwell2010

Turbo-Like Structures for Chaos Encoding and Decoding

Martin Hasler, Slobodan Kozic, Francisco Javier Escribano Aparicio

In this paper, we explain how to build a turbo-like structure with binary inputs and chaotic outputs for efficient coding and decoding in additive white Gaussian noise (AWGN). We analyze the convergence of the decoding algorithm, the performance in the err ...

2009

Early consensus in complex networks under variable graph topology

Martin Hasler, Leonidas Georgopoulos

Analysis of the linear algorithm for consensus on complex networks shows the existence of two distinct phases, the asymptotic and the transient. The network reaches the asymptotic when the components corresponding to the spectral gap eigenvalue of the weig ...

IEEE2009

Multiple task learning in recurrent neural networks using layered reservoirs

Martin Hasler, Ali Ajdari Rad, Mahdi Jalili

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

Low-Density Codes Based on Chaotic Systems for Low-Density Codes Based on Chaotic Systems for Simple Encoding

Martin Hasler, Slobodan Kozic

This paper proposes a new class of low-density generator-matrix codes (LDGM) based on chaotic dynamical systems. The codes are designed by controlling symbolic dynamics and using linear convolutional codes. Analyzing the complex structure of chaotic system ...

2009

Page 2 sur 6