Hello everyone,
I'm presenting to you a simple two hidden layers Neural Network system programmed in OOP style. It came along with a General Matrix library also programmed in OOP style and a NNTrainingData library also programmed in OOP style. The sources can be downloaded here : https://www.dropbox.com/s/srzw10oi55mnx ... k.zip?dl=0
There is another download link : http://gsaumure.x10host.com/forum/NeuralNetwork.zip
The Neural Network code is based on the "The Coding Train" following play list on YouTube : https://www.youtube.com/playlist?list=P ... 9by6XFdCfh
For now I have only tested the Neural Network with the XOR problem to see if it work and it does.
This code, in my case, will be used in my game project to program an AI of some sort.
Best regards
StarBootics
Neural Network
- StarBootics
- Addict
- Posts: 984
- Joined: Sun Jul 07, 2013 11:35 am
- Location: Canada
Neural Network
The Stone Age did not end due to a shortage of stones !
Re: Neural Network
Nice job !
Here, I am stuck with backpropagation in convolutive layer... I am waiting for coding train to explain it.
Here, I am stuck with backpropagation in convolutive layer... I am waiting for coding train to explain it.
There are 2 methods to program bugless.
But only the third works fine.
Win10, Pb x64 5.71 LTS
But only the third works fine.
Win10, Pb x64 5.71 LTS
- StarBootics
- Addict
- Posts: 984
- Joined: Sun Jul 07, 2013 11:35 am
- Location: Canada
Re: Neural Network
Thank you ! That being said I'm not in Image recognition processing Stuff. Maybe you can suggest a Coding challenge about that.Fig wrote:Nice job !
Here, I am stuck with backpropagation in convolutive layer... I am waiting for coding train to explain it.
The main purpose I'm looking for is a way to control Steering behaviors without overshooting right-left-right-left until I'm perfectly align with the direction I want the entity to go. Creating a functional Neural Network was the first step in that direction.
Best regards
StarBootics
The Stone Age did not end due to a shortage of stones !