Thursday 28th of March 2024
 

Spike Timing Dependent Competitive Learning in Recurrent Self Organizing Pulsed Neural Networks Case Study: Phoneme and Word Recognition


Tarek Behi, Najet Arous and Noureddine Ellouze

Synaptic plasticity seems to be a capital aspect of the dynamics of neural networks. It is about the physiological modifications of the synapse, which have like consequence a variation of the value of the synaptic weight. The information encoding is based on the precise timing of single spike events that is based on the relative timing of the pre- and post-synaptic spikes, local synapse competitions within a single neuron and global competition via lateral connections. In order to classify temporal sequences, we present in this paper how to use a local hebbian learning, spike-timing dependent plasticity for unsupervised competitive learning, preserving self-organizing maps of spiking neurons. In fact we present three variants of self-organizing maps (SOM) with spike-timing dependent Hebbian learning rule, the Leaky Integrators Neurons (LIN), the Spiking_SOM and the recurrent Spiking_SOM (RSSOM) models. The case study of the proposed SOM variants is phoneme classification and word recognition in continuous speech and speaker independent.

Keywords: Kohonen map, Leaky Integrators Neurons, Spiking_SOM, Recurrent Spiking_SOM, STDP, speech recognition.

Download Full-Text


ABOUT THE AUTHORS

Tarek Behi
Tarek BEHI received the MS degree in electrical engineering (signal processing) from National School of Engineer of Tunis (ENIT–Tunisia), is currently working towards the Ph.D. degree in electrical engineering (signal processing) from ENIT. He is currently a computer science assistant in the informatics department at FST, Tunisia. Her research interests include speech recognition, spiking neural networks, hierarchical neural networks and evolutionary neural networks.

Najet Arous
Najet AROUS received computer science engineering degree from Ecole Nationale des Sciences d’Informatique, Tunis, Tunisia, the MS degree in electrical engineering (signal processing) from the National School of Engineer of Tunis (ENIT–Tunisia), Tunisia, the Ph.D. degree in electrical engineering (signal processing) from ENIT. She is currently a computer science assisting master in the computer science department at FSM, Tunisia. Her research interests include scheduling optimization, speech recognition and evolutionary neural networks.

Noureddine Ellouze
Noureddine ELLOUZE received a Ph.D. degree in 1977 from l’Institut National Polytechnique at Paul Sabatier University (Toulouse-France), and Electronic Engineer Diploma from ENSEEIHT in 1968 at the same University. In 1978, Dr. Ellouze joined the Department of Electrical Engineering at the National School of Engineer of Tunis (ENIT– Tunisia), as ASSISTANT PROFESSOR in statistic, electronic, signal processing and computer architecture. In 1990, he became Professor in signal processing; digital signal processing and stochastic process. He has also served as director of electrical department at ENIT from 1978 to 1983. General manager and President of the Research Institute on Informatics and Telecommunication IRSIT from 1987-1990, and President of the Institut in 1990-1994. He is now Director of Signal Processing Research Laboratory LSTS at ENIT, and is in charge of Control and Signal Processing Master degree at ENIT. Pr Ellouze is IEEE fellow since 1987; he directed multiple Masters and Thesis and published over 200 scientific papers both in journals and proceedings. He is chief editor of the scientific journal Annales Maghrébines de l’Ingénieur. His research interest include neural networks and fuzzy classification, pattern recognition, signal processing and image processing applied in biomedical, multimedia, and man machine communication.


IJCSI Published Papers Indexed By:

 

 

 

 
+++
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »