A process for constructing multiple weighing value synapse nerve cell

A construction method and neuron technology, applied in the computer field, can solve problems such as waste of resources and time, inability to adapt to complex surfaces, waste, etc.

CN1464477AInactive Publication Date: 2003-12-31INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI
0 Cites 9 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2003-12-31
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

A process for constructing multiple weighing value synapse nerve cell comprising, (1) determining the number of the synapse, (2) constructing the multiple weighing value synapse, (3) selecting activation threshold according to synapse function and system characteristic, (4) forming the multiple weighing value synapse, (5) determining the threshold value according to synapse function, excitation function and synapse number.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of computers and provides a neuron construction method of multi-weight synapse. Background technique

[0002] Neuron is the basic unit of neural network and an important factor affecting the performance of neural network. A general neuron structure such as figure 1 shown. It can be seen from the figure that each input (synapse) of a neuron has only one weight, which is designed to simulate the structure of biological neurons. The mathematical expression of the neuron is as follows, where Y is the output of the neuron, X i for the nerve Y = f [ Σ i = 0 n W i X i - θ ] element input, W i is the input weight of the neuron, θ is th...

Examples

Embodiment

[0033] The technology patented in this application has been applied to the CASSANDRA-II neural computer, realizing a general neural network compatible with common neuron models and RBF neuron models. the neuron Y = f { Σ [ W i 1 ( X i - W i 2 ) | W i 1 ( X ...