Invention Grant
- Patent Title: Electrical networks using analytic loss gradients for design, analysis and machine learning
-
Application No.: US17875223Application Date: 2022-07-27
-
Publication No.: US11922296B2Publication Date: 2024-03-05
- Inventor: Jack David Kendall
- Applicant: Rain Neuromorphics Inc.
- Applicant Address: US CA San Francisco
- Assignee: Rain Neuromorphics Inc.
- Current Assignee: Rain Neuromorphics Inc.
- Current Assignee Address: US CA San Francisco
- Agency: Van Pelt, Yi & James LLP
- Main IPC: G06N3/063
- IPC: G06N3/063
Abstract:
A system includes inputs, outputs, and nodes between the inputs and the outputs. The nodes include hidden nodes. Connections between the nodes are determined based on a gradient computable using symmetric solution submatrices.
Public/Granted literature
- US20230040533A1 ELECTRICAL NETWORKS USING ANALYTIC LOSS GRADIENTS FOR DESIGN, ANALYSIS AND MACHINE LEARNING Public/Granted day:2023-02-09
Information query
