Xojo Neural Network Class
Xojo Neural Network Class 1.0
Xojo Neural Network Class allows you to implement an Artificial Convolutional Neural Network in your Xojo (REAL Studio) Applications.
You want to embed deep learning capacities into your Xojo (REAL Studio) Applications, via a simple, efficient and ready-to-use Artificial Convolutional Neural Network?
Then Xojo Neural Network Class is what you need!
- It's a single Class implementing a fully connected multi-layer perceptron with automatic feed-forward and back-propagation algorithm.
- You can set as many input neurones, hidden neurones and output neurones as you want.
- You can perform either supervised or unsupervised trainings.
- You can adjust the speed of the trainings via the usual Eta learning rate and Alpha momentum parameters.
- You can adjust the limit of the trainings via the usual maximum number of generations and maximum sum squared error parameters.
- You can perform mutations with the usual rate and amplitude parameters.
- You can save and load the Networks.
- It doesn't need any installation which makes it very easy to use.
- It is available in English (and soon in other languages).
Read the whole documentation for more details...
Information for Mac OS 10.14 Mojave users:
Under Mac OS 10.14 Mojave, if you're launching the Application for the first time, Mac OS' GateKeeper (which you can configure in the "System Preferences") will refuse to launch it because you've not downloaded it from the Mac App Store (but from our website). In this case, instead of double-clicking on it, all you have to do is to right-click on the Application's icon, and then select the "Open" menu. A message will appear in which you'll be able to confirm that you want to launch the Application (even if it was not downloaded from the Mac App Store from an Identified Developper).
NB: We're not distributing our Applications through the Mac App Store, because Apple's fees policy on the Mac App Store is not financially respectful of developers and small and medium companies, and consequently, at the end, of customers.