Invention Grant
- Patent Title: Memristive neuromorphic circuit and method for training the memristive neuromorphic circuit
-
Application No.: US14797284Application Date: 2015-07-13
-
Publication No.: US10332004B2Publication Date: 2019-06-25
- Inventor: Irina Kataeva , Dmitri B. Strukov , Farnood Merrikh-Bayat
- Applicant: DENSO CORPORATION , The Regents of the University of California
- Applicant Address: JP Kariya US CA Oakland
- Assignee: DENSO CORPORATION,The Regents of the University of California
- Current Assignee: DENSO CORPORATION,The Regents of the University of California
- Current Assignee Address: JP Kariya US CA Oakland
- Agency: Posz Law Group, PLC
- Main IPC: G06E1/00
- IPC: G06E1/00 ; G06N3/08 ; G06F11/07 ; G06N3/063

Abstract:
A neural network is implemented as a memristive neuromorphic circuit that includes a neuron circuit and a memristive device connected to the neuron circuit. An input voltage is sensed at a first terminal of a memristive device during a feedforward operation of the neural network. An error voltage is sensed at a second terminal of the memristive device during an error backpropagation operation of the neural network. In accordance with a training rule, a desired conductance change for the memristive device is computed based on the sensed input voltage and the sensed error voltage. Then a training voltage is applied to the memristive device. Here, the training voltage is proportional to a logarithmic value of the desired conductance change.
Public/Granted literature
- US20170017879A1 MEMRISTIVE NEUROMORPHIC CIRCUIT AND METHOD FOR TRAINING THE MEMRISTIVE NEUROMORPHIC CIRCUIT Public/Granted day:2017-01-19
Information query