公开(公告)号：US20220164669A1

公开(公告)日：2022-05-26

申请号：US17442111

申请日：2019-06-05

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Aojun Zhou ,  Dawei Sun ,  Dian Gu ,  Yurong Chen

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

Abstract: Systems, methods, apparatuses, and computer program products to receive a plurality of binary weight values for a binary neural network sampled from a policy neural network comprising a posterior distribution conditioned on a theta value. An error of a forward propagation of the binary neural network may be determined based on a training data and the received plurality of binary weight values. A respective gradient value may be computed for the plurality of binary weight values based on a backward propagation of the binary neural network. The theta value for the posterior distribution may be updated using reward values computed based on the gradient values, the plurality of binary weight values, and a scaling factor.

公开(公告)号：US20210019628A1

公开(公告)日：2021-01-21

申请号：US16981018

申请日：2018-07-23

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Dawei Sun ,  Aojun Zhou ,  Hao Zhao ,  Yurong Chen

IPC: G06N3/08 ,  G06N5/00 ,  G06N3/04

Abstract: Methods, systems, apparatus, and articles of manufacture are disclosed to train a neural network. An example apparatus includes an architecture evaluator to determine an architecture type of a neural network, a knowledge branch implementor to select a quantity of knowledge branches based on the architecture type, and a knowledge branch inserter to improve a training metric by appending the quantity of knowledge branches to respective layers of the neural network.