Announcing GPdotNET v5 and related Book

After one year of writing and coding, finally I  can announce my two big achievements which are related to each other:

1. The fifth version of my open source project GPdotNET – genetic programming tool, and

2. The book:Optimized Genetic Programming Applications: Emerging Research and Opportunities, published by IGI-GLobal.

Along the book, I was developing GPdotNET application which is explained in Chapter 5. Actually the Chapter 5 described in depth all aspects of the application, with real world examples.

As can be seen GPdotNET v5 is completely rewritten application, with new logo and GUI. As Introduction of the application I have prepared several videos on youtube with quick explanation how to use some of the main modules in GPdotNET.

Using ANNdotNET – GUI tool to create CNTK based model for Iris data set

In this tutorial we are going to create and train Iris model using ANNdotNET.  ANNdotNET is windows application for creating and training CNTK based models without leaving GUI.

2. Step: Open ANNdotNET application. Press New command, select Project 1 tree item and rename the project  into Iris Data Set.

2. Step: Select Data Command from Model Preparation ribbon group, Click File button from Import experimenal data dialog and select the recently downloaded file. Check Comma check box and press Import Data button.

3. Steps: Double click on Scaling for each column, and select MinMax normalization option from the popup ComboBox list. Double click on Type for the output column, and select Category, and 1:N for encoding. More information how to prepare data for ML you can find at https://bhrnjica.net/2018/03/01/data-preparation-tool-for-machine-learning/

4. Steps: Once the data is prepared Click Create Model Command and Model Settings panel is shown. Setup parameters as shown on the image below and click Run command.

5. Steps: Once the model is trained you can evaluate model by selecting Evaluate Command. Depending on the model type (regression, Binary or Multi class classification) The appropriate Evaluation dialog appears. Since this is multi class classification model, the Confusion matrix is shows, with micro and macron performance parameters.

6. Steps: For further analysis you can export model to Excel, or into ONNX. Also you can save the project which can later be opened and retrained again.

Note: Currently ANNdotNET is in alpha version, and more feature will come in near future.

ANNdotNET – the first GUI based CNTK tool

ANNdotNET is windows desktop application written in C# for creating and training ANN models. The application relies on Microsoft Cognitive Toolkit, CNTK, and it is supposed to be GUI tool for CNTK library with extensions in data preprocessing, model evaluation and exporting capabilities. It is hosted at GitHub and can be clone from http://github.com/bhrnjica/anndotnet

Currently, ANNdotNET supports the folowing type of ANN:

• Simple Feed Forward NN
• Deep Feed Forward NN
• Recurrent NN with LSTM

The process of creating, training, evaluating and exporting models is provided from the GUI Application and does not require knowledge for supported programming languages. The ANNdotNET is ideal for engineers which are not familiar with programming languages.

Software Requirements

ANNdotNET is x64 Windows desktop application which is running on .NET Framework 4.7.1. In order to run the application, the following requirements must be met:

– Windows 7, 8 or 10 with x64 architecture
– NET Framework 4.7.1
– CPU/GPU support.

Note: The application automatically detect GPU capability on your machine and use it in training and evaluation, otherwise it will use CPU.

How to run application

In order to run the application there are two possibilities:

Clone the GitHub repository of the application and open it in Visual Studio 2017.

1. Change build architecture into x64, build and run the application.

The following three short videos quickly show how to create, train and evaluate regression, binary and multi class classification models.

• Training regression model. Data set is Concrete Slump Test is downloaded from the UCI ML Repository and loaded into ANNdotNET without any modification, since the data preparation module can prepare it.

2. Training and evaluation binary classifier model. Data represent Titanic data set downloaded from the public repository.

3. Training and evaluation multi class classification models. Data represents Iris data set downloaded from the same page as above.

Announcement of GPdotNET v5 and ANNdotNET v1.0

As you already know GPdotNET v4 tool consists of several modules which include:

• GP module for creating and training models based on genetic programming,
• ANN module for creating and training models based on Feed Forward Neural Networks,
• GA module for model and function optimization using Genetic Algorithm
• LGA module is for  linear programming with GA which includes solving Traveling Salesman based problems, Assignment and Transportation problems.

With the latest release the GPdotNET has changed a lot. First of all, the initial idea about GPdotNET was to provide GP method in the application. And as the project grew lot of new implementations were included in the main project. This year I decided to make two different projects which can be seen as the natural evolution of GPdotNET v4.

The first project remain the same which follows the previous version and it is called GPdotNET v5. The project includes only GP related algorithm implementation which is developed for creating and training supervised ML problems (regression, binary and multi-class classification).

The second project uses several ANN algorithms for creating and training supervised machine learning problems.  The project is called ANNdotNET. It is Windows Forms desktop application very similar with GPdotNET, for creating and training ANN models.

I am very prod to announce that the new version of GPdotNET will be released as two  different open source projects.

1. GPdotNET v5 – which is hosted at the same address as previous. The older version GPdotNET v4 has moved at http://github.com/bhrnjica/gpdotnetv4  – and will be the latest version for non GP and ANN modules in GPdotNET.
2. ANNdotNET v1 – is hosted at separate repository http://github.com/bhrnjica/anndotnet.

Data Preparation Tool for Machine Learning

Regardless of machine learning library you use, the data preparation is the first and one of the most important step in developing predictive models. It is very often case that the data supposed to be used for the training is dirty with lot of unnecessary columns, full of missing values, un-formatted numbers etc. Before training the data must be cleaned and properly defined in order to get good model. This is known as data preparation. The data preparation consist of cleaning the data, defining features and labels, deriving the new features from the existing data, handling missing values, scaling the data etc.  It can be concluded that the total time we spend in ML modelling,the most of it is related to data preparation.

In this blog post I am going to present the simple tool which can significantly reduce the preparation time for ML. The tool simply loads the data in to GUI, and then the user can define all necessary information. Once the data is prepared user can store the data it to files which can be then directly imported into ML algorithm such as CNTK.

The following image shows the ML Data Preparation Tool main window.

From the image above, the data preparation can be achieved in several steps.

1. Load dirty data into ML Prep Tool, by pressing Import Data button
2. Transform the data by providing the flowing:
1. Type – each column can be:
1. Numeric – which holds continuous numeric values,
2. Binary – which indicates two class categorical data,
3. Category – which indicates categorical data with more than two classes,
4. String – which indicate the column will not be part of training and testing data set,
2. Encoding – in case of Binary and Category column type, the encoding must be defined. The flowing encoding is supported:
1. Binary Encoding with (0,1) – first binary values will be 0, and second binary values will be 1.
2. Binary encoding with (-1,1) – first binary values will be -1, and second binary values will be 1.
3. Category Level- which each class treats as numeric value. In case of 3 categories(R,G, B), encoding will be (0,1,2)
4. Category 1:N- implements One-Hot vector with N columns. In case of 3 categories(R,G, B), encoding will be R =  (1,0,0),G =  (0,1,0), B =  (0,0,1).
5. Category 1:N-1(0) – implements dummy coding with N-1 columns. In case of 3 categories(R, G, B), encoding will be R =  (1,0),G =  (0,1), B =  (0,0).
6. Category 1:N-1(-1) – implements dummy coding with N-1 columns. In case of 3 categories(R, G, B), encoding will be R =  (1,0),G =  (0,1), B =  (-1,-1).
3. Variable – defines features and label. Only one label, and at least one features can be defined. Also the column can be defined as Ignore variable, which will skip that column.  The following options are sported:
1. Input – which identifies the column as feature or predictor,
2. Output – which identifies the column as label or model output.
4. Scaling – defines column scaling. Two scaling options are supported:
1. MinMax,
2. Gauss Standardization,
5. Missing Values – defines the replacement for the missing value withing the column. There are several options related to numeric and two options (Random and Mode ) for categorical type.
3. Define the testing data set size by providing information of row numbers or percent.
4. Define export options
5. Press Export Button.

As can be seen this is straightforward workflow of data preparation.

Besides the general export options which can be achieved by selecting different delimiter options, you can export data set in to CNTK format, which is very handy if you play with CNTK.

After data transformations, the user need to check CNTK format int the export options and press Export in order to get CNTK training and testing files, which can be directly used in the code without any modifications.

Some of examples will be provided int he next blog post.

The project is hosted at GitHub, where the source code can be freely downloaded and used at this location: https://github.com/bhrnjica/MLDataPreparationTool .

In case you want only binaries, the release of version v1.0 is published here: https://github.com/bhrnjica/MLDataPreparationTool/releases/tag/v1.0

Using CNTK and C# to train Mario to drive Kart

Introduction

In this blog post I am going to explain one of possible way how to implement Deep Learning ML to play video game. For this purpose I used the following:

1.  N64 Nintendo emulator which can be found here,
2. Mario Kart 64 ROM, which can be found on internet as well,
3. CNTK – Microsoft Cognitive Toolkit
4. .NET Framework and C#

The idea behind this machine learning project is to capture images together with action, while you play Mario Kart game. Then captured images are transformed into features of training data set, and action keys into label hot vectors respectively.  Since we need to capture images, the emulator should be positioned at fixed location and size during playing the game, as well as during testing algorithm to play game. The flowing image shows N64 emulator graphics configuration settings.

Also the N64 emulator is positioned to Top-Left corned of screen, so it is easier to capture the images.

Data collection for training data set

During image captures game is played as you would play normally. Also no special agent, not platform is required.

In .NET and C# it is implemented image capture from the specific position of screen, as well as it is recorded which keys are pressed during game play. In order to record keys press, the code found here is modified and used.

The flowing image shows the position of N64 emulator with playing Mario Kart game (1), the windows which is capture and transform the image (2), and the application which collect images, and key press action and generated training data set into file(3).

The data is generated on the following way:

• each image is captured, resized to 100×74 pixels and gray scaled prior to be transformed and persisted to data set training file.
• before image is persisted the hotkey of action key press is recorded and connected to image.

So the training data is persisted into CNTK format which consist of:

1. |label – which represent 5 component hot vector, indicate: Forward, Break, Forward-Left, Forward-Right and None (1 0 0 0 0)
2. |features consist of 100×74 numbers which represent pixels of the images.

The following data sample shows how training data set are persisted in the txt file:

```|label 1 0 0 0 0 |features 202 202 202 202 202 202 204 189 234 209 199...
|label 0 1 0 0 0 |features 201 201 201 201 201 201 201 201 203 18...
|label 0 0 1 0 0 |features 199 199 199 199 199 199 199 199 199 19...
|label 0 0 0 1 1 |features 199 199 199 199 199 199 199 199 199 19...
```

Since my training data is more than 300 000 MB of size, I provided just few BM sized file, but you can generate file as big as you wish with just playing the game, and running the flowing code from Program.cs file:

await GenerateData.Start();

Training Model to play the game

Once we generate the data, we can move to the next step: training RCNN model to play the game. For training model the CNTK is used. Also since we play a game and previous sequence will determined the next sequence in the game, LSTM RNN is used. More information about CNTK and LSTM can be found in previous posts. In my case I have collected nearly 15000 images during several round of playing the same level and route. Also for more accurate model much more images should be collected, nearly 100 000. The model is trained in one hour, with 500000 iterations. The source code about whole project can be found on GitHub page. (http://github.com/bhrnjica/LSTMBotGame )

By running the following code, the training process is started with provided training data:

CNTKDeepNN.Train(DeviceDescriptor.GPUDevice(0));

Playing the game with CNTK model

Once we trained the model, we move to the next step: playing a game. The emulator should be positioned on the same position and with the same size in order to play the game.ONce the model is trained and created in th training folder, the playing game can be achive by running:

var dev = DeviceDescriptor.CPUDevice;
MarioKartPlay.PlayGame(dev);

How it looks like on my case, you can see on this youtube video:

CNTK 106 Tutorial – Time Series prediction with LSTM using C#

In this post will show how to implement CNTK 106 Tutorial in C#. This tutorial lecture is written in Python and there is no related example in C#. For this reason I decided to translate this very good tutorial into C#. The tutorial can be found at: CNTK 106: Part A – Time series prediction with LSTM (Basics)  and uses sin wave function in order to predict time series data. For this problem the Long Short Term Memory, LSTM, Recurrent Neural Network is used.

Goal

The goal of this tutorial is prediction the simulated data of a continuous function ( sin wave). From $N$ previous values of the $y=sin(t)$ function where $y$ is the observed amplitude signal at time $t$, prediction of  $M$ values of $y$ is going to predict for the corresponding future time points.

The excitement of this tutorial is using the LSTM recurrent neural network which is nicely suited for this kind of problems. As you probably know LSTM is special recurrent neural network which has ability to learn from its experience during the training. More information about this fantastic version of recurrent neural network can be found here.

The blog post is divided into several sub-sections:

1. Simulated data part
2. LSTM Network
3. Model training and evaluation

Since the simulated data set is huge, the original tutorial has two running mode which is described by the variable isFast. In case of fast mode, the variable is set to True, and this mode will be used in this tutorial. Later, the reader may change the value to False in order to see much better training model, but the training time will be much longer. The Demo for this this blog post exposes variables of the batch size and iteration number to the user, so the user may defined those numbers as he/she want.

Data generation

In order to generate simulated sin wave data, we are going to implement several helper methods. Let $N$ and $M$  be a ordered set of past values and future (desired predicted values) of the sine wave, respectively. The two methods are implemented:

1. generateWaveDataset()

The generateWaveDataset takes the periodic function,set of independent values (which is corresponded the time for this case) and generate the wave function, by providing the time steps and time shift. The method is related to the generate_data() python methods from the original tutorial.

```static Dictionary<string, (float[][] train, float[][] valid, float[][] test)> loadWaveDataset(Func<double, double> fun, float[] x0, int timeSteps, int timeShift)
{
////fill data
float[] xsin = new float[x0.Length];//all data
for (int l = 0; l < x0.Length; l++)
xsin[l] = (float)fun(x0[l]);

//split data on training and testing part
var a = new float[xsin.Length - timeShift];
var b = new float[xsin.Length - timeShift];

for (int l = 0; l < xsin.Length; l++)
{
//
if (l < xsin.Length - timeShift) a[l] = xsin[l]; // if (l >= timeShift)
b[l - timeShift] = xsin[l];
}

//make arrays of data
var a1 = new List<float[]>();
var b1 = new List<float[]>();
for (int i = 0; i < a.Length - timeSteps + 1; i++)
{
//features
var row = new float[timeSteps];
for (int j = 0; j < timeSteps; j++)
row[j] = a[i + j];
//create features row
//label row
b1.Add(new float[] { b[i + timeSteps - 1] });
}

//split data into train, validation and test data set
var xxx = splitData(a1.ToArray(), 0.1f, 0.1f);
var yyy = splitData(b1.ToArray(), 0.1f, 0.1f);

var retVal = new Dictionary<string, (float[][] train, float[][] valid, float[][] test)>();
return retVal;
}
```

Once the data is generated, three datasets should be created: train, validate and test dataset, which are generated by splitting the dataset generated by the above method. The following splitData method splits the original sin wave dataset into three datasets,

```static (float[][] train, float[][] valid, float[][] test) splitData(float[][] data, float valSize = 0.1f, float testSize = 0.1f)
{
//calculate
var posTest = (int)(data.Length * (1 - testSize));
var posVal = (int)(posTest * (1 - valSize));

return (data.Skip(0).Take(posVal).ToArray(), data.Skip(posVal).Take(posTest - posVal).ToArray(), data.Skip(posTest).ToArray());
}
```

In order to visualize the data, the Windows Forms project is created. Moreover, the ZedGraph .NET class library is used in order to visualize the data. The following picture shows the generated data.

Network modeling

As mentioned on the beginning of the blog post, we are going to create LSTM recurrent neural network, with 1 LSTM cell for each input. We have N inputs and each input is a value in our continuous function. The N outputs from the LSTM are the input into a dense layer that produces a single output. Between LSTM and dense layer we insert a dropout layer that randomly drops 20% of the values coming from the LSTM to prevent overfitting the model to the training dataset. We want use use the dropout layer during training but when using the model to make predictions we don’t want to drop values.

The description above can be illustrated on the following picture:

The implementation of the LSTM can be sumarize in one method, but the real implementation can be viewed in the demo sample which is attached with this blog post.
The following methods implements LSTM network depicted on the image above. The arguments for the method are already defined.

```public static Function CreateModel(Variable input, int outDim, int LSTMDim, int cellDim, DeviceDescriptor device, string outputName)
{

Func<Variable, Function> pastValueRecurrenceHook = (x) => CNTKLib.PastValue(x);

//creating LSTM cell for each input variable
Function LSTMFunction = LSTMPComponentWithSelfStabilization<float>(
input,
new int[] { LSTMDim },
new int[] { cellDim },
pastValueRecurrenceHook,
pastValueRecurrenceHook,
device).Item1;

//after the LSTM sequence is created return the last cell in order to continue generating the network
Function lastCell = CNTKLib.SequenceLast(LSTMFunction);

//implement drop out for 10%
var dropOut = CNTKLib.Dropout(lastCell,0.2, 1);

//create last dense layer before output
var outputLayer =  FullyConnectedLinearLayer(dropOut, outDim, device, outputName);

return outputLayer;
}
```

Training the network

In order to train the model, the nextBatch() method is implemented that produces batches to feed the training function. Note that because CNTK supports variable sequence length, we must feed the batches as list of sequences. This is a convenience function to generate small batches of data often referred to as minibatch.

```private static IEnumerable<(float[] X, float[] Y)> nextBatch(float[][] X, float[][] Y, int mMSize)
{

float[] asBatch(float[][] data, int start, int count)
{
var lst = new List<float>();
for (int i = start; i < start + count; i++) { if (i >= data.Length)
break;

}
return lst.ToArray();
}

for (int i = 0; i <= X.Length - 1; i += mMSize) { var size = X.Length - i; if (size > 0 && size > mMSize)
size = mMSize;

var x = asBatch(X, i, size);
var y = asBatch(Y, i, size);

yield return (x, y);
}
}
```

Note: Since the this tutorial is implemented as WinForms C# project which can visualize training and testing datasets, as well as it  can show the best found model during the training process, there are lot of other implemented methods which are not mentioned here, but can be found in the demo source code attached in this blog post.

Key Insight

When working with LSTM the user should pay attention on the following:

Since LSTM must work with axes with unknown dimensions, the variables should be defined on different way as we could saw in the previous blog posts. So the input and the output variable are initialized with the following code listing:

```// build the model
var feature = Variable.InputVariable(new int[] { inDim }, DataType.Float, featuresName, null, false /*isSparse*/);
var label = Variable.InputVariable(new int[] { ouDim }, DataType.Float, labelsName, new List<CNTK.Axis>() { CNTK.Axis.DefaultBatchAxis() }, false);
```

As specified in the original tutorial: “Specifying the dynamic axes enables the recurrence engine handle the time sequence data in the expected order. Please take time to understand how to work with both static and dynamic axes in CNTK as described here, the dynamic axes is key point in LSTM.
Now the implementation is continue with the defining learning rate, momentum, the learner and the trainer.

```
var lstmModel = LSTMHelper.CreateModel(feature, ouDim, hiDim, cellDim, device, "timeSeriesOutput");

Function trainingLoss = CNTKLib.SquaredError(lstmModel, label, "squarederrorLoss");
Function prediction = CNTKLib.SquaredError(lstmModel, label, "squarederrorEval");

// prepare for training
TrainingParameterScheduleDouble learningRatePerSample = new TrainingParameterScheduleDouble(0.0005, 1);
TrainingParameterScheduleDouble momentumTimeConstant = CNTKLib.MomentumAsTimeConstantSchedule(256);

IList<Learner> parameterLearners = new List<Learner>() {
Learner.MomentumSGDLearner(lstmModel.Parameters(), learningRatePerSample, momentumTimeConstant, /*unitGainMomentum = */true)  };

//create trainer
var trainer = Trainer.CreateTrainer(lstmModel, trainingLoss, prediction, parameterLearners);
```

Now the code is ready, and the 10 epochs should return acceptable result:

```
// train the model
for (int i = 1; i <= iteration; i++)
{
//get the next minibatch amount of data
foreach (var miniBatchData in nextBatch(featureSet.train, labelSet.train, batchSize))
{
var xValues = Value.CreateBatch<float>(new NDShape(1, inDim), miniBatchData.X, device);
var yValues = Value.CreateBatch<float>(new NDShape(1, ouDim), miniBatchData.Y, device);

//Combine variables and data in to Dictionary for the training
var batchData = new Dictionary<Variable, Value>();

//train minibarch data
trainer.TrainMinibatch(batchData, device);
}

if (this.InvokeRequired)
{
// Execute the same method, but this time on the GUI thread
this.Invoke(
new Action(() =>
{
//output training process
progressReport(trainer, lstmModel.Clone(), i, device);
}
));
}
else
{
//output training process
progressReport(trainer, lstmModel.Clone(), i, device);

}
}
```

Model Evaluation

Model evaluation is implemented during the training process. In this way we can see the learning process and how the model is getting better and better.

Fore each minibatch the progress method is called which updates the charts for the training and testing data set.

```void progressReport(Trainer trainer, Function model, int iteration, DeviceDescriptor device)
{
textBox3.Text = iteration.ToString();
textBox4.Text = trainer.PreviousMinibatchLossAverage().ToString();
progressBar1.Value = iteration;

reportOnGraphs(trainer, model, iteration, device);
}

private void reportOnGraphs(Trainer trainer, Function model, int i, DeviceDescriptor device)
{
currentModelEvaluation(trainer, model, i, device);
currentModelTest(trainer, model, i, device);
}
```

The following picture shows the training process, where the model evaluation is shown simultaneously, for the training and testing data set.
Also the simulation of the Loss value during the training is simulated as well.

As can be see the blog post extends the original Tutorial with some handy tricks during the training process. Also this demo is good strarting point for development bether tool for LSTM Time Series training. The full source code of this blog post, which shows much more implementation than presented in the blog post can be found here.