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

In this article Xiaobian for you to introduce in detail "matlab how to achieve discrete Hopfield neural network classification", the content is detailed, the steps are clear, the details are handled properly, I hope this "matlab how to achieve discrete Hopfield neural network classification" article can help you solve your doubts, following the editor's ideas slowly in-depth, together to learn new knowledge.

The weight correction method of the newhop () function in the MATLAB neural network toolbox is the orthogonalization method, not the outer product method. The weight coefficient matrix of Hopfield neural network is designed by orthogonal method.

Ensure the stability of the system in a studio, that is, its weights are symmetrical.

Ensure that all stable equilibrium points that require memory can converge to themselves.

Make the number of pseudo-stable points as small as possible

Make the stable point as attractive as possible.

% clear environment variables

Clear

Clc

Import data

Load class.mat

%% goal vector

T = [class _ 1 class_2 class_3 class_4 class_5]

Create network

Net=newhop (T)

Import samples to be classified

Load sim.mat

A = {[sim_1 sim_2 sim_3 sim_4 sim_5]}

%% Network Simulation

Y=sim (net, {25 20}, {}, A)

%% results show

Y1roomY {20} (:, 1:5)

Y2roomY {20} (:, 6:10)

Y3roomY {20} (:, 11:15)

Y4roomY {20} (:, 16:20)

Y5roomY {20} (:, 21:25)

%% drawing

Result= {Ttera {1}; Y {20}}

Figure

For packs 1 purl 3

For karma 1 purl 5

Subplot (3meme 5, (pmae1) * 5qk)

Temp=result {p} (:, (KMur1) * 5+1:k*5)

[mmaine n] = size (temp)

For iTunes 1PUM

For jungle 1purn

If temp (iMagnej) > 0

Plot (jpr mphiliPhony, "koji,"MarkerFaceColor."

Else

Plot (jrecom mcomijime ko')

End

Hold on

End

End

Axis ([0 60 0 12])

Axis off

If pendant 1

Title (['class' num2str (k)])

Elseif pendant 2

Title (['pre-sim' num2str (k)])

Else

Title (['sim' num2str (k)])

End

End

End

%

Noisy= [1-1-1-1-1-1

-1 1-1-1-1-1-1-1-1

1-1-1-1-1-1-1-1-1-1

-1-1-1-1-1-1-1-1-1-1-1

-1 1-1-1-1-1-1-1-1

-1-1-1-1-1]

Y=sim (net, {5100}, {}, {noisy})

Axiy {100}

Read here, this "matlab how to achieve discrete Hopfield neural network classification" article has been introduced, want to master the knowledge of this article also need to practice and use in order to understand, if you want to know more related articles, welcome to pay attention to 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.