A New Stochastic Computing Methodology for Efficient Neural Network Implementation

This paper presents a new methodology for the hardware implementation of neural networks (NNs) based on probabilistic laws. The proposed encoding scheme circumvents the limitations of classical stochastic computing (based on unipolar or bipolar encoding) extending the representation range to any rea...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transaction on neural networks and learning systems Ročník 27; číslo 3; s. 551 - 564
Hlavní autoři:	Canals, Vincent, Morro, Antoni, Oliver, Antoni, Alomar, Miquel L., Rossello, Josep L.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.03.2016 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Artificial neural networks Buildings Computation Computational intelligence Encoding Hardware Logic gates Mathematical functions Mathematical models Methodology Neural networks neural networks (NNs) pattern recognition Probabilistic logic stochastic systems Stochasticity Switches stochastic systems neural networks (NNs) probabilistic logic Computational intelligence pattern recognition
ISSN:	2162-237X, 2162-2388, 2162-2388
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!