Neural networks in Lisp - advice

Can anybody suggest a good tutorial or book for neural networks in Lisp, or a blog, or share some code sample?

I have experience with neural netowrks in the imperative languages C++, Java, C#, but I want to tr开发者_如何学Cy it in Lisp.

---

The seminal book AI: a modern approach includes LISP source code on the website: link Specifically, check out the Learning chapter (perceptron etc)

In the same vein you have Paradigms of AI in Lisp, but it doesn't really touch neural networks if I remember correctly.

---

While the question is old and my answer is late, I still think it's valuable.

Recently I was looking for some resources on Machine Learning in Common Lisp(hence why I found this question). After doing some more research, I've found this codebase. It contains many interesting things, such as Boltzmann Machines, feed-forward and recurrent backprop neural networks. The author also has other libraries, such as evolutionary algorithms. This code is sure a good way to start.

---

Yann LeCun, my advisor at NYU, wrote an object-oriented dialect of lisp called Lush while he worked at Bell Labs. It feels like a lispy MATLAB, and is geared towards quick prototyping of numerical experiments and machine learning research. It installs easily if you're using Linux or Mac OS. During the late 90's a good fraction of all checks in the US were being read by the LeNet-5 net that he wrote in Lush.

We use it for most of our research, since it has so much support for convolutional neural networks, linear algebra, and has an easy C/C++ FFI for everything else. It also comes with demo code for implementing neural nets and convolutional networks for image and character classification, which is probably where you'd want to start.

It's in the Ubuntu repositories, but you probably want the latest version from here:

http://lush.sourceforge.net/

---

Searching on google I found these

book: "Common LISP Modules Artificial Intelligence" (at amazon)
Same at Google Books
library for Fast Artificial Neural Network
And this blog have some posts about ANN