PyRCN: A Toolbox for Exploration and Application of Reservoir Computing Networks

2 code implementations • 8 Mar 2021 • Peter Steiner, Azarakhsh Jalalvand, Simon Stone, Peter Birkholz

In this paper, we show how to uniformly describe RCNs with small and clearly defined building blocks, and we introduce the Python toolbox PyRCN (Python Reservoir Computing Networks) for optimizing, training and analyzing RCNs on arbitrarily large datasets.

Time Series Time Series Prediction

Cluster-based Input Weight Initialization for Echo State Networks

1 code implementation • 8 Mar 2021 • Peter Steiner, Azarakhsh Jalalvand, Peter Birkholz

Echo State Networks (ESNs) are a special type of recurrent neural networks (RNNs), in which the input and recurrent connections are traditionally generated randomly, and only the output weights are trained.

Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems

no code implementations • 26 Jan 2021 • Utku Ozbulak, Baptist Vandersmissen, Azarakhsh Jalalvand, Ivo Couckuyt, Arnout Van Messem, Wesley De Neve

Another concern that is often cited when designing smart home applications is the resilience of these applications against cyberattacks.

Adversarial Attack Human Activity Recognition

Phoneme Recognition with Large Hierarchical Reservoirs

no code implementations • NeurIPS 2010 • Fabian Triefenbach, Azarakhsh Jalalvand, Benjamin Schrauwen, Jean-Pierre Martens

Automatic speech recognition has gradually improved over the years, but the reliable recognition of unconstrained speech is still not within reach.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1