Learning method of neural network circuit

摘要

A neuron circuit in a neural network circuit element includes a waveform generating circuit for generating a predetermined pulse voltage, and a first input signal has a waveform of the predetermined pulse voltage. For a period having a predetermined duration of the predetermined pulse voltage generated within the neural network circuit element including the variable resistance element which is applied with the first input signal from another neural network circuit element, the first input signal is permitted to be input to the control electrode of the variable resistance element, to change the resistance value of the variable resistance element due to an electric potential difference generated between the first electrode and the control electrode which occurs depending on an input timing of the first input signal with respect to the period during which the first input signal is permitted to be input to the control electrode.

主权项

1. A learning method of a neural network circuit including a plurality of neural network circuit elements which are interconnected,
wherein each of the plurality of neural network circuit elements includes:
at least one synapse circuit which receives an input a signal, as a first input signal, output from another neural network circuit element; andone neuron circuit which receives as an input a signal output from the at least one synapse circuit, wherein the synapse circuit includes a variable resistance element which includes:
a semiconductive layer having a first electrode; and a second electrode;a ferroelectric layer formed on a main surface of the semiconductive layer; anda control electrode formed on the ferroelectric layer, a resistance value between the first electrode and the second electrode changing in response to an electric potential difference between the first electrode and the control electrode, wherein the neuron circuit includes a waveform generating circuit for generating a predetermined pulse voltage, the predetermined pulse voltage being a bipolar sawtooth pulse voltage or a mexican-hat pulse voltage, and the first input signal has a waveform of the predetermined pulse voltage, wherein the method comprises:
for a period having a predetermined duration before and after a temporal mid point of a waveform of the predetermined pulse voltage generated within the neural network circuit element including the variable resistance element, inputting the first input signal from another neural network circuit element to the control electrode of the variable resistance element, to change the resistance value of the variable resistance element due to an electric potential difference generated between the first electrode and the control electrode which occurs depending on an input timing of the first input signal with respect to a period during which the first input signal is input to the control electrode of the variable resistance element.