Skip to content

An early simple artificial neural network is used for understand the training and working principles of neural networks. 一个能了解神经网络训练与测试结果的简单的神经网络.

License

Notifications You must be signed in to change notification settings

a2824256/Simple_HebbNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

HebbNet

An early simple artificial neural network is used for understand the training and working principles of neural networks. You can understand the working principle of the neural network according to the truth table of the two gates below.

Update History

Oct. 31 2018 - correct target calculation formula.

Train

Input X1, X2 and Y(Target). Then click the "Train" button. The weights will be changed.
Formula(target=y): new_weight[x] = old_weight[x] + input[x] × target

Test

Just enter X1 and X2. Then click the "Test" button. The trained network will calculate the Y(target) based on input.

Network Structure

image

AND gate truth table

X1 X2 Y
0 0 0
0 1 0
1 0 0
1 1 1

OR gate truth table

X1 X2 Y
0 0 0
0 1 1
1 0 1
1 1 1

Software View (Trainning and testing the AND gate)

image

About

An early simple artificial neural network is used for understand the training and working principles of neural networks. 一个能了解神经网络训练与测试结果的简单的神经网络.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages