Scilab module for artificial neural networks
DescriptionThis module implements artificial neural networks capabilities into the Scilab language. Current features are:
* Only layered feedforward networks are supported *directly* at the moment
(for others use the "hooks" provided)
* Unlimited number of layers
* Unlimited number of neurons per each layer separately
* User defined activation function (defaults to logistic)
* User defined error function (defaults to SSE)
* Algorithms implemented so far:
* standard (vanilla) with or without bias, on-line or batch
* momentum with or without bias, on-line or batch
* SuperSAB with or without bias, on-line or batch
* Conjugate gradients
* Jacobian computation
* Computation of result of multiplication between "vector" and Hessian
* Some helper functions provided
Upload new screenshots
Thanks for uploading more screenshots. Please note:
- Your screenshot should contain a typical scene when working with it.
- Take only a screenshot of the respective application and not of your whole desktop (unless the screenshot is meant for a window manager).
- Your screenshots must be in PNG format.
- You can upload multiple images at once.
- Your screenshot need to be approved by the moderators first. You will already see your screenshot but it will not be visible to others instantly. If moderators reject your upload you will get notified next time you visit this site (requires cookies).
- Images larger than 800x600 pixels will automatically be reduced. So don't try to capture too much detail in a screenshot. It may become unreadable. Shrink the applications window if possible.
- Screenshots are made public and can freely be used by anyone.
- Useful programs for making screenshots are shutter, ksnapshot (KDE), gimp, xwd or scrot. See the Debian wiki for more information on how to make screenshots under Debian.
- Please set your language to english so that everybody understands it. If you don't use english by default please start your application from a shell using after setting "export LANG=C".