Neural networks in VBA

[drgs]

If you guys have some experience from Pytorch or other major deep learning frameworks, and have some time to spare, give my simple neural network project (maybe the first one in VBA?) a test run. Big plus if you can test it with OpenBLAS dll which you put inside the same folder as the Excel workbook and edit the dll path in BlasFunctions module -- OpenBLAS provides prebuilt binary packages here https://sourceforge.net/projects/ope...files/v0.3.27/:

https://github.com/personalityson/VBANN

Option Explicit

Const MODEL_NAME As String = "MyModel"

Private m_oModel As Sequential

Public Sub SetupAndTrain()
    Dim lBatchSize As Long
    Dim lNumEpochs As Long
    Dim oTrainingSet As DataLoader
    Dim oTestSet As DataLoader
    
    VerifyOpenBlasLibrary
    
    lBatchSize = 10
    lNumEpochs = 50
    
    Set oTrainingSet = DataLoader(ImportDatasetFromWorksheet("ConcreteTrain", 8, 1, True), lBatchSize)
    Set oTestSet = DataLoader(ImportDatasetFromWorksheet("ConcreteTest", 8, 1, True), lBatchSize)
    
    Set m_oModel = Sequential(L2Loss(), SGDM())
    m_oModel.Add FullyConnectedLayer(8, 200)
    m_oModel.Add LeakyReLULayer()
    m_oModel.Add FullyConnectedLayer(200, 100)
    m_oModel.Add LeakyReLULayer()
    m_oModel.Add FullyConnectedLayer(100, 50)
    m_oModel.Add LeakyReLULayer()
    m_oModel.Add FullyConnectedLayer(50, 1)
    m_oModel.Fit oTrainingSet, oTestSet, lNumEpochs
    Serialize MODEL_NAME, m_oModel
    
    Beep
End Sub

Public Sub ContinueTraining()
    Dim lBatchSize As Long
    Dim lNumEpochs As Long
    Dim oTrainingSet As DataLoader
    Dim oTestSet As DataLoader

    VerifyOpenBlasLibrary
    
    lBatchSize = 10
    lNumEpochs = 50
    
    Set oTrainingSet = DataLoader(ImportDatasetFromWorksheet("ConcreteTrain", 8, 1, True), lBatchSize)
    Set oTestSet = DataLoader(ImportDatasetFromWorksheet("ConcreteTest", 8, 1, True), lBatchSize)
    
    Set m_oModel = Unserialize(MODEL_NAME)
    m_oModel.Fit oTrainingSet, oTestSet, lNumEpochs
    Serialize MODEL_NAME, m_oModel
    
    Beep
End Sub

Thanks

[reexre]

Hi
I am interested in NN.
I have implemented a simple one in VB6 that can evolve using backpropagation or Neuroevolution. (all from scratch)
https://www.vbforums.com/showthread....Neural-Network
I would like to try yours because I think it is more advanced (Deep). And maybe it could also be used for "style transfer" on images.

I have (sort of) never worked in VBA, so, do you have a VB6 version ?

[drgs]

Hi
I am interested in NN.
I have implemented a simple one in VB6 that can evolve using backpropagation or Neuroevolution. (all from scratch)
https://www.vbforums.com/showthread....Neural-Network
I would like to try yours because I think it is more advanced (Deep). And maybe it could also be used for "style transfer" on images.

I have (sort of) never worked in VBA, so, do you have a VB6 version ?

Hi,
For me it is the opposite -- I have never worked with VB6. I do rely on saving models to worksheets and reading data from worksheets, so I guess it won't work without modifications.

I only have very basic layers to put together a MLP, but by its modular design it's only a matter of adding new layer classes...
(Currently I'm trying to integrate an extra dll for vector math (Intel Performance Primitives) to speed things up, so I ended up rewriting a few thing.)

For style transfer on images you need at least convolutional layers + pooling layers, I think. Plus, a way to read images from disc, with color channels and everything.
It's possible, but not really what I intended it for

Btw, curious to have a peek at your code, but cant seem to find any source...

[reexre]

Thank you for reply

...
Btw, curious to have a peek at your code, but cant seem to find any source...

it's in the #2 post NNandGA.zip