Programmable output blocks for analog neural memory in a deep learning artificial neural network

Invention Grant

US11893478B2 Programmable output blocks for analog neural memory in a deep learning artificial neural network 有权

Please log in to see more content

Patent Title: Programmable output blocks for analog neural memory in a deep learning artificial neural network
Application No.: US17367542

Application Date: 2021-07-05
Publication No.: US11893478B2

Publication Date: 2024-02-06
Inventor: Hieu Van Tran
Applicant: Silicon Storage Technology, Inc.
Applicant Address: US CA San Jose
Assignee: SILICON STORAGE TECHNOLOGY, INC.
Current Assignee: SILICON STORAGE TECHNOLOGY, INC.
Current Assignee Address: US CA San Jose
Agency: DLA PIPER LLP US
Main IPC: G06N3/065
IPC: G06N3/065 ; G06N3/04

Programmable output blocks for analog neural memory in a deep learning artificial neural network

Abstract:

Numerous embodiments are disclosed for programmable output blocks for use with a VMM array within an artificial neural network. In one embodiment, the gain of an output block can be configured by a configuration signal. In another embodiment, the resolution of an ADC in the output block can be configured by a configuration signal.

Public/Granted literature

US20210334639A1 PROGRAMMABLE OUTPUT BLOCKS FOR ANALOG NEURAL MEMORY IN A DEEP LEARNING ARTIFICIAL NEURAL NETWORK Public/Granted day:2021-10-28

Information query

Espacenet