US 12,260,337 B2
Performing inference and training using sparse neural network
Subutai Ahmad, Palo Alto, CA (US); and Luiz Scheinkman, Sunnyvale, CA (US)
Assigned to Numenta, Inc., Redbwood City, CA (US)
Filed by Numenta, Inc., Redwood City, CA (US)
Filed on May 4, 2023, as Appl. No. 18/312,011.
Application 18/312,011 is a continuation of application No. 16/696,991, filed on Nov. 26, 2019, granted, now 11,681,922.
Prior Publication US 2023/0274150 A1, Aug. 31, 2023
Int. Cl. G06N 3/084 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/084 (2013.01) [G06N 3/04 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving input data by a neural network including a plurality of layers of nodes including a current layer and a previous layer;
generating a layer output of the previous layer based at least on the input data;
increasing sparsity of a set of weights that represents connections between nodes of the current layer and nodes of the previous layer to generate a sparsified set of weights that indicates each of the nodes of the current layer as having a predetermined number of connections to the nodes of the previous layer;
applying, to the layer output of the previous layer, the sparsified set of weights;
generating intermediate outputs for the current layer by applying the set of weights for the current layer to a layer output of the previous layer; and
generating a layer output for nodes of the current layer by increasing sparsity of the intermediate outputs.