Invention Grant
US06983265B2 Method to improve the data transfer rate between a computer and a neural network
失效
提高计算机和神经网络之间数据传输速率的方法
- Patent Title: Method to improve the data transfer rate between a computer and a neural network
- Patent Title (中): 提高计算机和神经网络之间数据传输速率的方法
-
Application No.: US10316250Application Date: 2002-12-10
-
Publication No.: US06983265B2Publication Date: 2006-01-03
- Inventor: Pascal Tannhof , Ghislain Imbert de Tremiolles
- Applicant: Pascal Tannhof , Ghislain Imbert de Tremiolles
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agent H. Daniel Schnurmann
- Priority: EP01480142 20011221
- Main IPC: G06N3/06
- IPC: G06N3/06

Abstract:
A method is described to improve the data transfer rate between a personal computer or a host computer and a neural network implemented in hardware by merging a plurality of input patterns into a single input pattern configured to globally represent the set of input patterns. A base consolidated vector (U′*n) representing the input pattern is defined to describe all the vectors (Un, . . . , Un+6) representing the input patterns derived thereof (U′n, . . . , U′n+6) by combining components having fixed and ‘don't care’ values. The base consolidated vector is provided only once with all the components of the vectors. An artificial neural network (ANN) is then configured as a combination of sub-networks operating in parallel. In order to compute the distances with an adequate number of components, the prototypes are to include also components having a definite value and ‘don't care’ conditions. During the learning phase, the consolidated vectors are stored as prototypes. During the recognition phase, when a new base consolidated vector is provided to ANN, each sub-network analyses a portion thereof After computing all the distances, they are sorted one sub-network at a time to obtain the distances associated to each vector.
Public/Granted literature
- US20030135475A1 Method to improve the data transfer rate between a computer and a neural network Public/Granted day:2003-07-17
Information query