BP neural network algorithm

The BP (Back Propagation) network was proposed in 1986 by a group of scientists headed by Rumelhart and McCelland. It is a multi-layer feedforward network trained according to the error back propagation algorithm. It is currently the most widely used neural network model. one.

BP network can learn and store a large number of input-output pattern mapping relationships without revealing in advance the mathematical equations describing this mapping relationship.

Its learning rule is to use the steepest descent method and continuously adjust the weights and thresholds of the network through backpropagation to minimize the sum of square errors of the network. The topology structure of BP neural network model includes input layer, hidden layer and output layer. (Recommended learning: web front-end video tutorial)

BP neural network algorithm is proposed based on the existing algorithm of BP neural network, through arbitrary selection With a set of weights, the given target output is directly used as the algebraic sum of linear equations to establish a system of linear equations. The solution requires weighting. There is no local minimum and slow convergence problems of traditional methods, and it is easier to understand.

BP algorithm

The artificial neural network (ANN) system appeared after the 1940s. It is adjustable by numerous neurons. It is connected by connection weights and has the characteristics of large-scale parallel processing, distributed information storage, and good self-organization and self-learning capabilities. It is increasingly widely used in the fields of information processing, pattern recognition, intelligent control, and system modeling. .

In particular, the error back-propagation training (BP network) can approximate any continuous function, has strong nonlinear mapping capabilities, and the number of intermediate layers of the network and the processing units of each layer Parameters such as the number and the learning coefficient of the network can be set according to the specific situation, and the flexibility is great, so it plays an important role in many application fields.

In order to solve the shortcomings of BP neural network such as slow convergence speed, inability to guarantee convergence to the global maximum point, lack of theoretical guidance in selecting the middle layer of the network and the number of its units, and instability of network learning and memory, this method was proposed Many improved algorithms.

The above is the detailed content of BP neural network algorithm. For more information, please follow other related articles on the PHP Chinese website!