Computing with spikes: architecture, properties and implementation,Used

Computing with spikes: architecture, properties and implementation,Used

In Stock
SKU: DADAX3659203947
Brand: LAP Lambert Academic Publishing
Condition: New
Regular price$107.59
Quantity
Add to wishlist
Add to compare

Sold by Ergodebooks, an authorized reseller.

Returns accepted within 30 days | support@ergodebooks.com

Verified
Shipping Information
  • Free Standard Shipping — United States only
  • Processing Time: 1–3 business days
  • Estimated Delivery: 3–5 business days after dispatch
  • Double-boxed, fully insured & discreetly packaged
  • Tracking number sent via email once dispatched
  • Orders over $250 require signature upon delivery. Taxes calculated at checkout.
Returns & Refund

Returns accepted within 30 days of delivery.

Damaged or Defective Item

Free return shipping + replacement or full refund

Wrong Item Received

Free return shipping + replacement or full refund

Change of Mind

Return shipping at customer's expense · 25% restocking fee applies

All returns require a Return Authorization (RA) number before sending.

To initiate a return, contact us:

support@ergodebooks.com +1 (281) 738-1050
View Full Return & Refund Policy
Payment Option
Payment Methods

Help

If you have any questions, you are always welcome to contact us. We'll get back to you as soon as possible, withing 24 hours on weekdays.

Customer service

All questions about your order, return and delivery must be sent to our customer service team by e-mail at yourstore@yourdomain.com

Sale & Press

If you are interested in selling our products, need more information about our brand or wish to make a collaboration, please contact us at press@yourdomain.com

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 discretetime 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 NPcomplete problem (when both weights and interneural 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 inputoutput transformation for learning the implicit parameters of the corresponding transfer function.

⚠️ WARNING (California Proposition 65):

This product may contain chemicals known to the State of California to cause cancer, birth defects, or other reproductive harm.

For more information, please visit www.P65Warnings.ca.gov.

Recently Viewed