CNIPA.AI
返回搜索
档案

ARCHITECTURAL AUGMENTATION OF NEURAL NETWORKS USING EVALUATED SPECIALTY NODE UNITS

发明专利审中
30权利要求 · 2 独立
§ Ⅰ

卷宗概要

发明人

James K. Baker; Bradley J. Baker

IPC 分类

G6N 3/82G6F 16/901G6F 18/21G6F 18/214G6F 18/24G6N 3/4G6N 3/45G6N 3/48G6N 3/8G6N 3/84G6N 5/46G6N 20/G6N 20/20H4L 67/142

CPC 分类

G6N3/82G6F16/9024G6F18/214G6F18/217G6F18/24G6N3/4G6N3/45G6N3/48G6N3/8G6N3/84G6N20/G6N20/20H4L67/142G6F18/2148G6N5/46

A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

原文(中文)

A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.