JavaTM classes for implementing Feedforward, Simple Recurrent and Random-Order Recurrent Neural Nets trained by Backpropagation. Questions? Feel free to drop by and chat if you have any questions - one of us is usually around during normal CST/CDT business hours. havBpNet:J is the first Java version of our popular havBpNet++ (C++) Neural Net class library. As such, it is focused on implementation of the underlying NN functions/activities rather than the higher-level simulator/UI. It is designed to be fully embedable; however, it can, as easily, be used to implement stand-alone training or consultation applications or applets. The typical application can take advantage of the layer oriented API to define either simple nets or very complicated and large nets consisting of one or more sub-nets. Individual and Site Licenses of the havBpNet:JTM class library, can be purchased online using all Major Credit Cards, approved Purchase Orders or US Checks - Phone, Fax and Wire Transfer orders are also available. Frequently Asked Questions Below are answers to several fairly often asked questions about havBpNet:J. You might also take a look at the Online Documentation if you need more detailed answers. Alternatively, you are welcome to give us a call at (281) 341-5035 in order to discuss you application and how the hav.Software Neural Net libraries can help.

	How about an online demo? Yes. We made a little javascript demo (long ago when Javascript was first introduced) which performs consultation of a 3 layer feed forward net to solve a simple parity problem and a 3-D Feature Map which classifies 5x7 bit maps of the uppercase Roman alphabet. The FF net used was trained using the havBpNet++ Class Library and the FM net was trained using the havFmNet++ Class Library. You're welcome to play with the Javascript FF and FM Consultation online demo.
	What sort of restrictions are there in terms of layer size (number of nodes) and number of layers? There are no realistic restrictions imposed by the library. In fact, however, your platform does impose certain restrictions - for example, the number of nodes in a collection of connected layers cannot exceed the maximum positive int on your platform. You can still create nets (or composite nets) that total more nodes than this restriction's limit by using "Copy" rather than "Direct" connections between layers.
	What network parameters are implemented? havBpNet:J implements all standard feed-forward/backprop parameters such as Beta (learning-rate), Mu (momentum), Error Threshold, Cascade-coefficient and weight-decay. Five activation-functions are suppported. These are Linear, Logistic-Sigmoid, Hyperbolic-tangent, sin and Hermite. Three error functions are supported. These are Squared (e^2), Cube (e^3) and Quad (e^4). Both pattern-by-pattern and batch training modes are supported. In pattern-by-pattern mode, you may choose either interleved or non-interleved weight updates. In batch mode, you have control over the batch size. Bias is supported in such a way that you can use one bias node for all layers or have a bias-node for each layer or some sub-set of layers. Typical applications will utilize the layer-API, so parameters are assigned to layers; however, more sophisticated developers can use direct node access methods to effect parameters on a per node basis.
	Is Recurrency supported? In addition to supporting the standard cascade-coeficient, havBpNet:J supports two forms of recurrency. First, the typical Sequential Net weighted-copy recurrency (a la Jordan or Elman). Second, a layer may be connected as input to itself or to "lower" layers in the net. This form of recurrency is supported with Random-Ordered train and cycle messages that causes the node in a layer to be processed in a random order, thus reducing the skew effect that would otherwise occur. Full Backprop-through-time is not yet implemented but may be supported in future versions of havBpNet:J.
	How are layers saved? havBpNet:J is not tied to a specific database. As delivered, networks are saved to flat-files and thus avoid the requirement for additional DB support. If you have a prefered DB, it should be a fairly "simple" thing for you to modify the Save and Restore methods to utilize the DB's API. Network SAVE files can be shared between Nets built with havBpNet:J and havBpNet++.
	How are sub-nets connected together? havBpNet:J supports both direct connection and intermediate-Copy connections between sub-nets.
	What platforms can I use? havBpNet:J is written entirely in Java and should work on any Java Virtual Machine - 1.0 or later.