Question

Duplicate

What are some good resources for learning about Artificial Neural Networks?

I'm looking for a good (beginner level) reference book (or website) on different types of Neural Nets/their applications/examples. I don't have any particular application in mind, I'm just curious as to how I can make use of them. I'm specifically interested in using them with Python, but any language, or even just theory would do fine.

Was it helpful?

Solution

There is quite a extensive series of courses avaliable at Heaton Research. The course is for C# (Avaliable also for Java) however it explains the concepts at length, so I suggest you take a look at it even if you will code in python yourself.

The courses are in video format, however most important concepts are also writen down.

OTHER TIPS

See the below three links for Neural Networks using Python:

An Introduction to Neural Networks

Weave a Neural Net with Python

Neural Networks in Pyro

Ron Stephens

"Programming collective intelligence" by Toby Segaran has a chapter about NN and also some examples in Python.

You might want to try out A Brief Introdruction to Neural Networks by David Kriesel. It's a richly illustrated ebook, and it's available for free. It covers lots of Network paradigms and is less theoretical than the ebook of Rojas. Seems to be the best on the web that you can get for free

AI-Junkie has a very good intuitive tutorial about neural networks. The site is designed to minimize the required mathematics so that the tutorial is accessible.

I am currently using this site as a primer - not python, but a good feed-forward network example and pretty straightforward to follow.

At the same time I have been reading The Essence of Neural Networks by Robert Callan (ISBN 0-13-908732-X) which has a wide range of network architectures and applications and is an easy read.

Since you mention python I should direct you to this IBM site, which I found very useful and the underlying code is in python here. Citation should go to Neil Schemenauer.

I should also mention that I took the python code and ported it to numpy because it ran very slowly. I was unsuccessful, but before I rubbish numpy I have to say that I suspect my implementation was not very good and I'm sure there is a vectorised way of doing forward passes and backpropagations, I just didn't find it.

What I have ended up doing is implementing in Java by a simple port of the python code. This only took an hour or so and it runs about 100 times faster. I think this is more proof that I don't know what I'm doing with numpy, but if you are starting from scratch I would question whether raw python is the right language for you. You may be better coding this sort of thing in C or C++ if you have to use python.

Best of luck.

I think you have the python bit covered with the answers given above. As for the "or even just theory", Raúl Rojas has a hefty ebook you can download from his wiki page.

The best reference is "Neural Networks for Pattern Recognition", by Bishop. Another good book is "Neural Networks and Learning Machines", by Haykin.

More practical references include the user guides of the Neural Network Toolbox for Matlab or the Open Source Neural Networks C++ Library Flood.

FAQ ANN newsgroup comp.ai.neural-nets archieves usable online or offline

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