In this work we studied at a practical level how computation with action potentials (spikes) can be performed. We address the problem of programming of a dynamical system modeled as a neural network and considering both, hardware and software implementations. For this, we considered a discrete-time spiking neuron model, which was introduced by Soula et al. in 2006, and called BMS. On one hand, we proposed an efficient method to properly estimate the parameters (delayed synaptic weights) of a neural network from the observation of its spiking dynamics. Thus, the idea was to avoid the underlying NP-complete problem (when both weights and inter-neural transmission delays are considered in the parameters estimation). So far, our method defines a Linear Programming (LP) system to perform the parameters estimation. Another aspect considered in this work was the fact that we included a reservoir computing mechanism (hidden network) as to increase the computational power as to add robustness. Furthermore, these ideas are applied to implement input-output transformation for learning the implicit parameters of the corresponding transfer function.

*"synopsis" may belong to another edition of this title.*

Horacio Rostro Gonzalez, Postdoctoral Research Fellow: Neural Engineering at Universiy of Cyprus. Dsc: Computational Neuroscience at University of Nice-Sophia Antipolis. MEng: Instrumentation and Digital Systems at University of Guanajuato. He is currently an Associate Professor within the Department of Electronics at the University of Guanajuato

*"About this title" may belong to another edition of this title.*

Published by
LAP Lambert Academic Publishing 2012-08-14
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
paperback
Quantity Available: > 20

Seller:

Rating

**Book Description **LAP Lambert Academic Publishing 2012-08-14, 2012. paperback. Condition: New. Seller Inventory # 9783659203947

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Quantity Available: 1

Seller:

Rating

**Book Description **Condition: New. Publisher/Verlag: LAP Lambert Academic Publishing | architecture, properties and implementation | In this work we studied at a practical level how computation with action potentials (spikes) can be performed. We address the problem of programming of a dynamical system modeled as a neural network and considering both, hardware and software implementations. For this, we considered a discrete-time spiking neuron model, which was introduced by Soula et al. in 2006, and called BMS. On one hand, we proposed an efficient method to properly estimate the parameters (delayed synaptic weights) of a neural network from the observation of its spiking dynamics. Thus, the idea was to avoid the underlying NP-complete problem (when both weights and inter-neural transmission delays are considered in the parameters estimation). So far, our method defines a Linear Programming (LP) system to perform the parameters estimation. Another aspect considered in this work was the fact that we included a reservoir computing mechanism (hidden network) as to increase the computational power as to add robustness. Furthermore, these ideas are applied to implement input-output transformation for learning the implicit parameters of the corresponding transfer function. | Format: Paperback | Language/Sprache: english | 168 pp. Seller Inventory # K9783659203947

Published by
LAP Lambert Academic Publishing
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Quantity Available: > 20

Seller:

Rating

**Book Description **LAP Lambert Academic Publishing, 2012. PAP. Condition: New. New Book. Delivered from our UK warehouse in 4 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000. Seller Inventory # LQ-9783659203947

Published by
LAP Lambert Academic Publishing
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Quantity Available: > 20

Seller:

Rating

**Book Description **LAP Lambert Academic Publishing, 2012. PAP. Condition: New. New Book. Shipped from US within 10 to 14 business days. THIS BOOK IS PRINTED ON DEMAND. Established seller since 2000. Seller Inventory # IQ-9783659203947

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Quantity Available: 5

Seller:

Rating

**Book Description **Condition: New. Seller Inventory # ria9783659203947_ing

Published by
LAP Lambert Academic Publishing Aug 2012
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Taschenbuch
Quantity Available: 1

Seller:

Rating

**Book Description **LAP Lambert Academic Publishing Aug 2012, 2012. Taschenbuch. Condition: Neu. Neuware - In this work we studied at a practical level how computation with action potentials (spikes) can be performed. We address the problem of programming of a dynamical system modeled as a neural network and considering both, hardware and software implementations. For this, we considered a discrete-time spiking neuron model, which was introduced by Soula et al. in 2006, and called BMS. On one hand, we proposed an efficient method to properly estimate the parameters (delayed synaptic weights) of a neural network from the observation of its spiking dynamics. Thus, the idea was to avoid the underlying NP-complete problem (when both weights and inter-neural transmission delays are considered in the parameters estimation). So far, our method defines a Linear Programming (LP) system to perform the parameters estimation. Another aspect considered in this work was the fact that we included a reservoir computing mechanism (hidden network) as to increase the computational power as to add robustness. Furthermore, these ideas are applied to implement input-output transformation for learning the implicit parameters of the corresponding transfer function. 168 pp. Englisch. Seller Inventory # 9783659203947

Published by
LAP Lambert Academic Publishing Aug 2012
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Taschenbuch
Quantity Available: 1

Seller:

Rating

**Book Description **LAP Lambert Academic Publishing Aug 2012, 2012. Taschenbuch. Condition: Neu. Neuware - In this work we studied at a practical level how computation with action potentials (spikes) can be performed. We address the problem of programming of a dynamical system modeled as a neural network and considering both, hardware and software implementations. For this, we considered a discrete-time spiking neuron model, which was introduced by Soula et al. in 2006, and called BMS. On one hand, we proposed an efficient method to properly estimate the parameters (delayed synaptic weights) of a neural network from the observation of its spiking dynamics. Thus, the idea was to avoid the underlying NP-complete problem (when both weights and inter-neural transmission delays are considered in the parameters estimation). So far, our method defines a Linear Programming (LP) system to perform the parameters estimation. Another aspect considered in this work was the fact that we included a reservoir computing mechanism (hidden network) as to increase the computational power as to add robustness. Furthermore, these ideas are applied to implement input-output transformation for learning the implicit parameters of the corresponding transfer function. 168 pp. Englisch. Seller Inventory # 9783659203947

Published by
LAP LAMBERT Academic Publishing
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Paperback
Quantity Available: 10

Seller:

Rating

**Book Description **LAP LAMBERT Academic Publishing, 2012. Paperback. Condition: New. This item is printed on demand. Seller Inventory # INGM9783659203947

Published by
LAP Lambert Academic Publishing Aug 2012
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Taschenbuch
Quantity Available: 1

Seller:

Rating

**Book Description **LAP Lambert Academic Publishing Aug 2012, 2012. Taschenbuch. Condition: Neu. This item is printed on demand - Print on Demand Neuware - In this work we studied at a practical level how computation with action potentials (spikes) can be performed. We address the problem of programming of a dynamical system modeled as a neural network and considering both, hardware and software implementations. For this, we considered a discrete-time spiking neuron model, which was introduced by Soula et al. in 2006, and called BMS. On one hand, we proposed an efficient method to properly estimate the parameters (delayed synaptic weights) of a neural network from the observation of its spiking dynamics. Thus, the idea was to avoid the underlying NP-complete problem (when both weights and inter-neural transmission delays are considered in the parameters estimation). So far, our method defines a Linear Programming (LP) system to perform the parameters estimation. Another aspect considered in this work was the fact that we included a reservoir computing mechanism (hidden network) as to increase the computational power as to add robustness. Furthermore, these ideas are applied to implement input-output transformation for learning the implicit parameters of the corresponding transfer function. 168 pp. Englisch. Seller Inventory # 9783659203947

Published by
LAP Lambert Academic Publishing, Germany
(2012)

ISBN 10: 3659203947
ISBN 13: 9783659203947

New
Paperback
Quantity Available: 10

Seller:

Rating

**Book Description **LAP Lambert Academic Publishing, Germany, 2012. Paperback. Condition: New. Aufl.. Language: English . Brand New Book ***** Print on Demand *****.In this work we studied at a practical level how computation with action potentials (spikes) can be performed. We address the problem of programming of a dynamical system modeled as a neural network and considering both, hardware and software implementations. For this, we considered a discrete-time spiking neuron model, which was introduced by Soula et al. in 2006, and called BMS. On one hand, we proposed an efficient method to properly estimate the parameters (delayed synaptic weights) of a neural network from the observation of its spiking dynamics. Thus, the idea was to avoid the underlying NP-complete problem (when both weights and inter-neural transmission delays are considered in the parameters estimation). So far, our method defines a Linear Programming (LP) system to perform the parameters estimation. Another aspect considered in this work was the fact that we included a reservoir computing mechanism (hidden network) as to increase the computational power as to add robustness. Furthermore, these ideas are applied to implement input-output transformation for learning the implicit parameters of the corresponding transfer function. Seller Inventory # AAV9783659203947