Title:
MEMRISTIVE NEUROMORPHIC CIRCUIT AND METHOD FOR TRAINING THE MEMRISTIVE NEUROMORPHIC CIRCUIT
Document Type and Number:
WIPO Patent Application WO/2017/010049
Kind Code:
A1
Abstract:
A neural network (10) is implemented as a memristive neuromorphic circuit that includes a neuron circuit (112, 114) and a memristive device (113) connected to the neuron circuit (112, 114). An input voltage is sensed at a first terminal of the memristive device (113) during a feedforward operation of the neural network (10). An error voltage is sensed at a second terminal of the memristive device (113) during an error backpropagation operation of the neural network (10). In accordance with a training rule, a desired conductance change for the memristive device (113) is computed based on the sensed input voltage and the sensed error voltage. Then a training voltage is applied to the memristive device (113). Here, the training voltage is proportional to a logarithmic value of the desired conductance change.
More Like This:
| WO/2022/145769 | METHOD AND APPARATUS FOR CALCULATING IMAGE QUALITY THROUGH IMAGE CLASSIFICATION |
| JPH0346195 | SYNAPTIC CELL FOR ASSOCIATIVE NETWORK |
| WO/2019/219618 | SWITCHED ARTIFICIAL SYNAPSE |
Inventors:
KATAEVA IRINA (JP)
STRUKOV DMITRI B (US)
MERRIKH-BAYAT FARNOOD (US)
STRUKOV DMITRI B (US)
MERRIKH-BAYAT FARNOOD (US)
Application Number:
PCT/JP2016/003001
Publication Date:
January 19, 2017
Filing Date:
June 22, 2016
Export Citation:
Assignee:
DENSO CORP (JP)
UNIV CALIFORNIA (US)
UNIV CALIFORNIA (US)
International Classes:
G06N3/063
Foreign References:
| US20110004579A1 | 2011-01-06 | |||
| US20030154175A1 | 2003-08-14 | |||
| US20120011090A1 | 2012-01-12 | |||
| US20150178619A1 | 2015-06-25 | |||
| US20120218807A1 | 2012-08-30 |
Other References:
JO, SUNG HYUN ET AL.: "Nanoscale Memristor Device as Synapse in Neuromorphic Systems", NANO LETT, 2010, pages 1297 - 1301, XP055200946
CANTLEY, KURTIS D. ET AL.: "Hebbian Learning in Spiking Neural Networks With Nanocrystalline Silicon TFTs and Memristive Synapses", IEEE TRANSACTIONS ON NANOTECH, vol. 10, 13 January 2011 (2011-01-13), pages 1066 - 1073, XP011359218
CANTLEY, KURTIS D. ET AL.: "Hebbian Learning in Spiking Neural Networks With Nanocrystalline Silicon TFTs and Memristive Synapses", IEEE TRANSACTIONS ON NANOTECH, vol. 10, 13 January 2011 (2011-01-13), pages 1066 - 1073, XP011359218
Attorney, Agent or Firm:
KIN, Junhi (JP)
Download PDF: