Modeling Algorithm (vi)--Neural network model

(a) Introduction to neural networks

The main use of computer computing power, a large number of samples to fit, and finally get a result we want, the result is 0-1 code, so OK

(ii) Artificial neural network model I. Three basic elements of the basic unit

1, a group of connections (input), which contains the strength of the connection (weight value).

2, a summation unit

3, a non-linear activation function, play the role of nonlinear mapping, and the neuron output amplitude limited to a certain extent (in (0,1) or ( -1,1))

4. There is also a threshold (bias)

It boils down to the following:

PS: You can also choose to add the bias (threshold) to the linear sum inside

5, the Activation function selection

Second, the network structure and working mode 1, feed-forward network

It is mainly used for pattern recognition and function approximation.

2. Feedback Network

Used as a variety of Lenovo memory, for solving optimization problems.

(iii) The problem of midges and the multilayer Feedforward Network I. Classification of midges and insect pests

Second, multilayer Feedforward network

1, input Layer 2, respectively, the length of the antennae and wings, only responsible for input

2, the processing layer has 3 (through the experiment or certain experience to determine), has the responsibility calculates

3, the output layer has 2, is responsible for the calculation

Then we have to use the existing data to determine the weight, the method used for the backward propagation algorithm

Third, backward propagation algorithm

Then it solves a nonlinear programming problem, which can be solved by using the method in the previous section.

The solution of the classification problem of midges

CLEAR;P1=[1.24,1.27    1.36,1.74    1.38,1.64    1.38,1.82    1.38,1.90    1.40,1.70    1.48,1.82    1.54,1.82    1.56,2.08];p 2=[1.14,1.82    1.18,1.96    1.20,1.86    1.26,2.00    1.28,2.00    1.30,1.96];p=[P1;P2]';Pr=Minmax (p); goal=[ones (1,9), Zeros (1,6) Zeros (1,9), Ones (1,6)]; Plot (P1 (:,1), p1 (:,2),'h', P2 (:,1), P2 (:,2),'o') Net=NEWFF (pr,[3,2],{'Logsig','Logsig'}); Net.trainParam.show=Ten; NET.TRAINPARAM.LR=0.05; Net.trainParam.goal=1e-Ten; Net.trainParam.epochs=50000; NET=train (net,p,goal); x=[1.24 1.80     1.28  1.84     1.40  2.04]';y0=Sim (net,p) y=sim (net,x)

Modeling Algorithm (vi)--Neural network model