Question

I want to implement a very simple neural net in VB.NET. I have array of integer, that is actually unmapped from black and white bitmap - we can assume every integer is 1 or 0. There is 1 spot painted on the bitmap, nothing else. I want to create and train the neural network to tell me if it's more like: 1-circle 2-square 3-horizontal line 4-vertical line 5-horizontal ellipse 6-vertical ellipse 7-horizontal and vertical elipses merged 8-vertical and horizontal elipses merged 9-2horizontal elipses merged And the shapes are really ugly, but a person can clearly make this decision, so I think a NN can be easily trained to do that. But I'm new to neural networks, and I have no idea how to approach the problem, for example different spots have various sizes so I don't know how to get fixed number of inbuts to feed in my NN - resizing is not an option

Was it helpful?

Solution

One option would be to use an existing Neural Net implementation, I'd recommend checking out the Accord.Net libary and the corresponding Accord.Neuro namespace.

Neural nets have been used successfully for handwriting recognition, which may be close to your problem. Check out the article Classifying Digits with Deep Belief Nets which includes a sample using Accord.Net.

Note: you would need hand labelled set of data to train the neural net with.

Licensed under: CC-BY-SA with attribution
Not affiliated with StackOverflow
scroll top