California Scientific      BrainMaker Neural Network Software
Home	Applications	What Are Neural Networks	Products	Ordering Info	Tech Support

What are NN's Designing NN's MMX Computers References Reviews of BrainMaker Why BM is best Products BrainMaker BrainMaker Professional Competitor Genetic Training Intro to NN Book Do I need Professional? NN Books For Sale Ordering Info International Shipping Order Form Price List Upgrade Order Form Tech Support Running Competitor Financial Networks Is my data OK? Using hidden neurons Large datasets BrainMaker's precision Predicting Horses Setting Min/Max Year 2000 Article Reprints Testing Concrete Decoding Sequences Hospital Costs Downloads MMX test software order form upgrade form Pro Forma invoice Applications Stocks Currency Predictions Corporate Bonds S&P 500 Index Stock Price Prediction Stock Prophet Natural Gas Prices Business Direct Mail Credit Scoring Real Estate Appraisal Bad Cops Finding Gold Jury Summoning Highway Maintenance Medical Breast Cancer Hospital Expenses Functional Recovery Heart Attack Diagnosis ER Test ordering Psychiactric Care Giant Cell Arteritis Sports Thoroughbreds Thoroughbreds 1 Dog Racing Science Solar Flares Protein Sequencing Mosquito Identification Spectroscopy Weather Forecasting Predicting El Nino Air Quality Manufacturing Welding Quality Plastics Testing IC Quality Control Paper Quality Concrete Testing Beer Quality Enzyme Synthesis Steam Quality Pattern Recog. Speech Recognition Article Classification Working with Chaos Chemical Drawings Sequence Prediction

Using Runtime.DLL with Visual Basic BrainMaker Pro comes with runtime.dll, which you use to run a trained network from your own program. Your program can be in C or Visual Basic. Visual Basic requires routines in DLLs to use the __stdcall calling convention, while C-callable routines use the __cdecl calling convention. The runtime dll has two sets of exported routines: one set for use from C and the other for use from Visual Basic. The Visual Basic routines have the same names but prepended with the prefix "std" and using the __stdcall convention. Following is an example of VB declaration code: Declare Function InitializeNetwork _ Lib "Runtime.dll" Alias "stdInitializeNetwork" _ (ByVal NetworkFilename As String) As Long Declare Function ProcessInputVector _ Lib "Runtime.dll" Alias "stdProcessInputVector" _ (ByVal NetHandle As Long, ByRef InVal As Single, ByRef OutVal As Single) _ As Long Declare Sub TerminateNetwork _ Lib "Runtime.dll" Alias "stdTerminateNetwork" _ (ByVal NetHandle As Long) Note that you declare the function InitializeNetwork but that this refers to the function stdInitializeNetwork in the dll, which is the one you want. Ditto for the other two. Now here is sample code to run the network: Private Sub Command1_Click() Dim inputs(1) As Single Dim outputs(3) As Single Dim prompt As String NetHandle = InitializeNetwork("logic.net") inputs(0) = 0 inputs(1) = 1 result = ProcessInputVector(NetHandle, inputs(0), outputs(0)) prompt = "Output values are " & outputs(0) & " " _ & outputs(1) & " " _ & outputs(2) & " " & outputs(3) MsgBox (prompt) TerminateNetwork (NetHandle) End Sub VBTest.zip - an example of using the BrainMaker Professional Runtime system in VB. The runtime dll lets you use trained networks with large numbers of inputs and outputs. logic.net has 2 inputs and 4 outputs. The function ProcessInputVectors takes the network handle and two vectors, one for the inputs and one for the outputs; these vectors can be quite long. In the example code, it looks like only one input is being passed, because you pass "inputs(0)" instead of the whole vector "inputs"; remember, however, that Visual Basic passes arguments by reference (that's what ByRef means), so inputs(0) is the address of the entire inputs vector, and similarly for outputs. So in your application, you still pass inputs(0) as in the example code, but inputs and outputs must be dimensioned large enough to hold all the inputs and outputs.

Home	Applications	What Are Neural Networks	Products	Ordering Info	Tech Support
California Scientific      BrainMaker Neural Network Software