公开(公告)号：US20230033694A1

公开(公告)日：2023-02-02

申请号：US17270404

申请日：2020-04-14

Applicant: Google LLC

Inventor： Ryan McDonald ,  Luis Sarmento

IPC: G06N3/04 ,  G06N3/08

Abstract: Persistent storage contains a representation of a neural network including an input layer, and output layer, and a hidden layer, wherein nodes of the hidden layer incorporate serialized activation functions, wherein the serialized activation functions for each of the nodes include a sigmoid function and a Beta function, wherein the sigmoid function is applied to weighted outputs from nodes of a previous layer of the neural network, wherein the Beta function is applied to a conductance hyper-parameter and respective outputs of the sigmoid function, and wherein outputs of the Beta function are provided to a subsequent layer of the neural network. One or more processors are configured to train the neural network until the outputs of the sigmoid function for the nodes of the hidden layer are substantially binary.

公开(公告)号：US12277490B2

公开(公告)日：2025-04-15

申请号：US17270404

申请日：2020-04-14

Applicant: Google LLC

Inventor： Ryan McDonald ,  Luis Sarmento

IPC: G06N3/048 ,  G06N3/088

Abstract: Persistent storage contains a representation of a neural network including an input layer, and output layer, and a hidden layer, wherein nodes of the hidden layer incorporate serialized activation functions, wherein the serialized activation functions for each of the nodes include a sigmoid function and a Beta function, wherein the sigmoid function is applied to weighted outputs from nodes of a previous layer of the neural network, wherein the Beta function is applied to a conductance hyper-parameter and respective outputs of the sigmoid function, and wherein outputs of the Beta function are provided to a subsequent layer of the neural network. One or more processors are configured to train the neural network until the outputs of the sigmoid function for the nodes of the hidden layer are substantially binary.