Copy-pasted example code from README

jorgenkg / python-neural-network

This is an efficient implementation of a fully connected neural network in NumPy. The network can be trained by a variety of learning algorithms: backpropagation, resilient backpropagation and scaled conjugate gradient learning. The network has been developed with PYPY in mind.

BSD 2-Clause "Simplified" License

297 stars 98 forks source link

Copy-pasted example code from README #23

Closed mvrozanti closed 7 years ago

mvrozanti commented 7 years ago

After 150.000 epochs I understood that this is not working as expected -- it doesn't diminish the error.

jorgenkg commented 7 years ago

Learning the XOR is a complex task if the network is only given a with few nodes to work with. Try to increase the number of nodes in the hidden layer or restart the learning process.

The math behind the network is correct.

mvrozanti commented 7 years ago

It was my fault. I set up something wrong. Ran it again and done in a second!

Great work sorry for the alarm

jorgenkg commented 7 years ago

That's ok. Feel free to post any questions if you run into trouble