Shulou(Shulou.com)06/01 Report--

Editor to share with you the radial basis function network RBF example analysis, I believe that most people do not know much about it, so share this article for your reference, I hope you will learn a lot after reading this article, let's go to know it!

The radial basis function network is a feedforward network composed of three layers: the first layer is the input layer, the number of nodes is equal to the dimension of the input, the second layer is the hidden layer, and the number of nodes depends on the complexity of the problem, and the third layer is the output layer. the number of nodes is equal to the dimension of the output data. Radial basis network is different from multi-layer perceptrons, its different layers have different functions, and the hidden layer is nonlinear. Radial basis function is used as the basis function. Thus, the input vector space is transformed into the hidden layer space, so that the original linear inseparable problem becomes linearly separable, and the output layer is linear.

%% fit the function with noise through radial basis function neural network

Please 1, 5, 5, 10

Rand ('state',pi)

T=sin (2quop) + rand (1penny length (P))

% add noise to the sine function

Plot (PMagna T.J.')

Net=newrb (P <... = 'class1' > 0. 6)

Test=1:.2:10

Out=sim (net,test)

Test calculates the corresponding function value for the new input value

Figure (1)

Hold on

Plot (test,out,'b-')

Legend ('input data', 'fitting function')

%% fit the function with noise through radial basis function neural network

Tic

Poseidon 2, 2, 2, 2, 2, 2, 2

Rand ('state',pi)

T = P.^ 2 + rand (1)

% add noise to the quadratic function

Net=newrbe (Pdome Tp3)

To establish a strict radial basis function network

Test=-2:.1:2

Out=sim (net,test)

% Simulation Test

Toc

Figure (1)

Plot (PMagna T.J.')

Hold on

Plot (test,out,'b-')

Legend ('input data', 'fitting function')

%% Radial basis function

N =-5VL 0.1RU 5

A = radbas (n Mel 2)

The center position is translated two units to the right.

B = exp (- (n). ^ 2Universe 2)

% divided by 2, the curve is more "chunky".

Figure

Plot (njol a)

Hold on

Plot (nrecom bjinghewi')

% dotted line

C = diff (a)

% calculate the differential of a

Hold off

Figure

Plot (c)

%% probabilistic neural network is suitable for classification problems.

Rng ('default')

A=rand (8 dint 2) * 10

% input training samples, 8 two-dimensional vectors

P=ceil (a)

Tc= [2,1,1,1,2,1,2,1]

% expected output

Plot (1), p (1), p (1), 2),'o')

Hold on

Plot (p), p ([2pyrm 3rect 4je 6je 8], 1), p ([2rect 3recorder 4je 6je 8], 2),'+')

Legend ('category I', 'category II')

Axis ([0pr 8pr 1pr 9])

Hold off

T=ind2vec (tc)

Net=newpnn (pendant dint t)

% Design PNN network

Y=sim (net,p')

% Simulation

Yc=vec2ind (y)

% actual output equals expected output

%% Generalized regression Neural Network is often used in function approximation

P = [1 2 3]

% training input vector

T = [2.0 4.1 5.9]

Expected output value of% training input

Plot (PMAE T.J.)

Net = newgrnn (PMAE T)

% Design GRNN network

X = [1.5, 2.5]

% test output. Calculate the lookup for xboxes 1.5 and 2.5

Y=sim (net,x)

% Test results

Hold on

Plot (xmeme yjinbo')

The above is all the contents of this article "example Analysis of Radial basis function Network RBF". Thank you for reading! I believe we all have a certain understanding, hope to share the content to help you, if you want to learn more knowledge, welcome to follow the industry information channel!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.