US 12,217,164 B2
Neural network and its information processing method, information processing system
Xinyi Li, Beijing (CN); Huaqiang Wu, Beijing (CN); He Qian, Beijing (CN); Bin Gao, Beijing (CN); Sen Song, Beijing (CN); and Qingtian Zhang, Beijing (CN)
Assigned to TSINGHUA UNIVERSITY, Beijing (CN)
Appl. No. 16/964,435
Filed by Tsinghua University, Beijing (CN)
PCT Filed Feb. 24, 2018, PCT No. PCT/CN2018/077087
§ 371(c)(1), (2) Date Jul. 23, 2020,
PCT Pub. No. WO2019/144453, PCT Pub. Date Aug. 1, 2019.
Claims priority of application No. 201810069603.5 (CN), filed on Jan. 24, 2018.
Prior Publication US 2021/0049448 A1, Feb. 18, 2021
Int. Cl. G06N 3/06 (2006.01); G06N 3/049 (2023.01); G06N 3/065 (2023.01); G06N 3/084 (2023.01)
CPC G06N 3/065 (2023.01) [G06N 3/049 (2013.01); G06N 3/084 (2013.01)] 11 Claims
OG exemplary drawing
 
1. A neural network circuit, comprising:
N neuron layers connected one by one, wherein except for a first neuron layer, each neuron in other neuron layers comprises m dendrite units and one soma unit;
wherein the dendrite units each comprises a capacitor and a diode in series and a resistance gradient element, the soma unit comprises a resistance mutation element and an oscillating circuit, and the m dendrite units are configured with different threshold voltages or currents respectively; and
neurons in an n-th neuron layer are respectively connected to the m dendrite units of each neuron in an (n+1)th neuron layer;
wherein N is an integer greater than or equal to 2, m is an integer greater than 1, n is an integer greater than or equal to 1 and less than N;
wherein outputs of the m dendrite units conform to the following function:

OG Complex Work Unit Math
where a denotes a nonlinear coefficient, which comprises a threshold voltage or current of the dendrite unit; x represents an input of the m dendrite units, and y represents the outputs of the m dendrite units.