US 11,748,607 B2
Systems and methods for partial digital retraining
Kurt F. Busch, Laguna Hills, CA (US); Jeremiah H. Holleman, III, Irvine, CA (US); Pieter Vorenkamp, Laguna Beach, CA (US); and Stephen W. Bailey, Irvine, CA (US)
Assigned to Syntiant, Aliso Viejo, CA (US)
Filed by Syntiant, Aliso Viejo, CA (US)
Filed on Jul. 27, 2018, as Appl. No. 16/48,099.
Claims priority of provisional application 62/539,384, filed on Jul. 31, 2017.
Prior Publication US 2019/0034790 A1, Jan. 31, 2019
Int. Cl. G06N 3/06 (2006.01); G06F 17/18 (2006.01); G06N 3/08 (2023.01); G06N 5/04 (2023.01); G06N 3/10 (2006.01); G06N 3/065 (2023.01); G06N 5/046 (2023.01)
CPC G06N 3/065 (2023.01) [G06F 17/18 (2013.01); G06N 3/08 (2013.01); G06N 3/105 (2013.01); G06N 5/046 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A neuromorphic integrated circuit, comprising: a multi-layered analog-digital hybrid neural network comprising a plurality of analog layers configured to include synaptic weights between neural nodes of the neural network for decision making by the neural network; wherein a positively weighted product may be stored in a first column of an analog multiplier array, and a negatively weighted product can be stored in a second column of the analog multiplier array; and at least one digital layer; wherein the digital layer is configured for programmatically compensating for weight drifts of the synaptic weights of the neural network, thereby maintaining integrity of the decision making by the neural network; and wherein the plurality of analog layers is disposed between a plurality of data inputs and the digital layer, and wherein the digital layer is disposed between the plurality of analog layers and a plurality of data outputs, wherein the positively and negatively weighted products can be taken as a differential current value.