A Method for Building Partially Connected Neural Network

Download Now
Provided by: Academy Publisher
Topic: Security
Format: PDF
In this paper the authors focus mainly on application of Partial Connected Back Propagation neural network (PCBP) instead of typical Fully Connected Back Propagation neural network (FCBP), as PCBP with less connections learns faster than FCBP. The initial neural network is fully connected, after training with sample data, a clustering method is employed to cluster weights between inputs to hidden layer and from hidden to output layer, and connections that are relatively unnecessary are deleted, thus the initial network becomes a PCBP network. PCBP can be used in prediction or data mining by training it with data that comes from database.
Download Now

Find By Topic