Primary direction neural network system

Abstract

The invention discloses a primary direction neural network system with a four-layer feedforward structure. The primary direction neural network system comprises an input layer, a first hidden layer, a second hidden layer and an output layer, wherein the input layer comprises D neurons, the first hidden layer comprises K groups of neurons, each group of the neurons comprises three neurons, the second hidden layer comprises K neurons, the output layer is a neuron, and both the D and the K are natural numbers; the input layer is used for receiving the D dimensional vector, and each neuron correspondingly receives one component in the D dimensional vector; the first hidden layer is used for mapping the D dimensional vector received from the input layer to the neurons in the second hidden layer, and each group of the neurons in the first hidden layer corresponds to one neuron in the second hidden layer; the second hidden layer is used for mapping the 3K dimensional vector received from the first hidden layer to the neurons in the output layer; and the output layer performs biased w0 linear weighting to the result of the second hidden layer and then outputs the result. The invention overcomes the extremely small difficulty of being trapped in local and the sensitivity to the noise.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a main direction neural network system. Background technique [0002] The problem of machine learning research is how to make the machine learn and become intelligent. Artificial neural network is a powerful means to realize machine learning, because the basic starting point of artificial neural network research is to imitate biological neural network. [0003] The artificial neural network is composed of a large number of neurons interconnected. The function of a single neuron can be very simple, but the network formed by the complex connection between them has extremely strong nonlinear mapping, distributed storage, parallel processing and fault tolerance. These are the foundations for realizing intelligence. [0004] The very important advantage of the artificial neural network lies in the realization of nonlinear map approximation, which is a very critical p...

AI Technical Summary

Problems solved by technology

But they all have disadvantages, for example, the BP network converges slowly and is easy to fall into the local minimum of the performance function; the RBF network is more sensitive to noise

Images