Poker Neural Network Example

1. Neural Network Examples
2. Artificial Neural Network Examples
3. Neural Network Example Python
4. Neural Network C++ Code Example

Editor’s note: One of the central technologies of artificial intelligence is neural networks. In this interview, Tam Nguyen, a professor of computer science at the University of Dayton, explains how neural networks, programs in which a series of algorithms try to simulate the human brain work.

Recurrent Neural Network(RNN) are a type of Neural Network where the output from previous step are fed as input to the current step.In traditional neural networks, all the inputs and outputs are independent of each other, but in cases like when it is required to predict the next word of a sentence, the previous words are required and hence there is a need to remember the previous words. Dreams,memories,ideas,self regulated movement, reflexes and everything you think or do is all generated through this process: millions, maybe even billions of neurons firing at different rates and making connections which in turn create different subsystems all running in parallel and creating a biological Neural Network. Artificial Neural Networks (ANN) are a mathematical construct that ties together a large number of simple elements, called neurons, each of which can make simple mathematical decisions. Together, the neurons can tackle complex problems and questions, and provide surprisingly accurate answers. A shallow neural network.

What are some examples of neural networks that are familiar to most people?

There are many applications of neural networks. One common example is your smartphone camera’s ability to recognize faces.

Driverless cars are equipped with multiple cameras which try to recognize other vehicles, traffic signs and pedestrians by using neural networks, and turn or adjust their speed accordingly.

Neural networks are also behind the text suggestions you see while writing texts or emails, and even in the translations tools available online.

Does the network need to have prior knowledge of something to be able to classify or recognize it?

Yes, that’s why there is a need to use big data in training neural networks. They work because they are trained on vast amounts of data to then recognize, classify and predict things.

In the driverless cars example, it would need to look at millions of images and video of all the things on the street and be told what each of those things is. When you click on the images of crosswalks to prove that you’re not a robot while browsing the internet, it can also be used to help train a neural network. Only after seeing millions of crosswalks, from all different angles and lighting conditions, would a self-driving car be able to recognize them when it’s driving around in real life.

More complicated neural networks are actually able to teach themselves. In the video linked below, the network is given the task of going from point A to point B, and you can see it trying all sorts of things to try to get the model to the end of the course, until it finds one that does the best job.

Some neural networks can work together to create something new. In this example, the networks create virtual faces that don’t belong to real people when you refresh the screen. One network makes an attempt at creating a face, and the other tries to judge whether it is real or fake. They go back and forth until the second one cannot tell that the face created by the first is fake.

Humans take advantage of big data too. A person perceives around 30 frames or images per second, which means 1,800 images per minute, and over 600 million images per year. That is why we should give neural networks a similar opportunity to have the big data for training.

How does a basic neural network work?

A neural network is a network of artificial neurons programmed in software. It tries to simulate the human brain, so it has many layers of “neurons” just like the neurons in our brain. The first layer of neurons will receive inputs like images, video, sound, text, etc. This input data goes through all the layers, as the output of one layer is fed into the next layer.

Let’s take an example of a neural network that is trained to recognize dogs and cats. The first layer of neurons will break up this image into areas of light and dark. This data will be fed into the next layer to recognize edges. The next layer would then try to recognize the shapes formed by the combination of edges. The data would go through several layers in a similar fashion to finally recognize whether the image you showed it is a dog or a cat according to the data it’s been trained on.

These networks can be incredibly complex and consist of millions of parameters to classify and recognize the input it receives.

Why are we seeing so many applications of neural networks now?

Actually neural networks were invented a long time ago, in 1943, when Warren McCulloch and Walter Pitts created a computational model for neural networks based on algorithms. Then the idea went through a long hibernation because the immense computational resources needed to build neural networks did not exist yet.

Recently, the idea has come back in a big way, thanks to advanced computational resources like graphical processing units (GPUs). They are chips that have been used for processing graphics in video games, but it turns out that they are excellent for crunching the data required to run neural networks too. That is why we now see the proliferation of neural networks.

[Understand new developments in science, health and technology, each week.Subscribe to The Conversation’s science newsletter.]

Code that accompanies this article can be downloaded here.

Back in 2015. Google released TensorFlow, the library that will change the field of Neural Networks and eventually make it mainstream. Not only that TensorFlow became popular for developing Neural Networks, it also enabled higher-level APIs to run on top of it. One of those APIs is Keras. Keras is written in Python and it is not supporting only TensorFlow. It is capable of running on top of CNTK and Theano. In this article, we are going to use it only in combination with TensorFlow, so if you need help installing TensorFlow or learning a bit about it you can check my previous article. There are many benefits of using Keras, and one of the main ones is certainly user-friendliness. API is easily understandable and pretty straight-forward. Another benefit is modularity. A Neural Network (model) can be observed either as a sequence or a graph of standalone, loosely coupled and fully-configurable modules. Finally, Keras is easily extendable.

Installation and Setup

As mentioned before, Keras is running on top of TensorFlow. So, in order for this library to work, you first need to install TensorFlow. Another thing I need to mention is that for the purposes of this article, I am using Windows 10 and Python 3.6. Also, I am using Spyder IDE for the development so examples in this article may variate for other operating systems and platforms. Since Keras is a Python library installation of it is pretty standard. You can use “native pip” and install it using this command:

Or if you are using Anaconda you can install Keras by issuing the command:

Alternatively, the installation process can be done by using Github source. Firstly, you would have to clone the code from the repository:

After that, you need to position the terminal in that folder and run the install command:

Sequential Model and Keras Layers

One of the major points for using Keras is that it is one user-friendly API. It has two types of models:

• Sequential model
• Model class used with functional API

Sequential model is probably the most used feature of Keras. Essentially it represents the array of Keras Layers. It is convenient for the fast building of different types of Neural Networks, just by adding layers to it. There are many types of Keras Layers, too. The most basic one and the one we are going to use in this article is called Dense. It has many options for setting the inputs, activation functions and so on. Apart from Dense, Keras API provides different types of layers for Convolutional Neural Networks, Recurrent Neural Networks, etc. This is out of the scope of this post, but we will cover it in fruther posts. So, let’s see how one can build a Neural Network using Sequential and Dense.

In this sample, we first imported the Sequential and Dense from Keras. Than we instantiated one object of the Sequential class. After that, we added one layer to the Neural Network using function add and Dense class. The first parameter in the Dense constructor is used to define a number of neurons in that layer. What is specific about this layer is that we used input_dim parameter. By doing so, we added additional input layer to our network with the number of neurons defined in input_dim parameter. Basically, by this one call, we added two layers. First one is input layer with two neurons, and the second one is the hidden layer with three neurons.

Another important parameter, as you may notice, is activation parameter. Using this parameter we define activation function for all neurons in a specific layer. Here we used ‘relu’ value, which indicates that neurons in this layer will use Rectifier activation function. Finally, we call add method of the Sequential object once again and add another layer. Because we are not using input_dim parameter one layer will be added, and since it is the last layer we are adding to our Neural Network it will also be the output layer of the network.

Iris Data Set Classification Problem

Like in the previous article, we will use Iris Data Set Classification Problem for this demonstration. Iris Data Set is famous dataset in the world of pattern recognition and it is considered to be “Hello World” example for machine learning classification problems. It was first introduced by Ronald Fisher, British statistician and botanist, back in 1936. In his paper The use of multiple measurements in taxonomic problems, he used data collected for three different classes of Iris plant: Iris setosa, Iris virginica, and Iris versicolor.

This dataset contains 50 instances for each class. What is interesting about it is that first class is linearly separable from the other two, but the latter two are not linearly separable from each other. Each instance has five attributes:

• Sepal length in cm
• Sepal width in cm
• Petal length in cm
• Petal width in cm
• Class (Iris setosa, Iris virginica, Iris versicolor)

In next chapter we will build Neural Network using Keras, that will be able to predict the class of the Iris flower based on the provided attributes.

Code

Keras programs have similar to the workflow of TensorFlow programs. We are going to follow this procedure:

Neural Network Examples

• Import the dataset
• Prepare data for processing
• Create the model
• Training
• Evaluate accuracy of the model
• Predict results using the model

Training and evaluating processes are crucial for any Artificial Neural Network. These processes are usually done using two datasets, one for training and other for testing the accuracy of the trained network. In the real world, we will often get just one dataset and then we will split them into two separate datasets. For the training set, we usually use 80% of the data and another 20% we use to evaluate our model. This time this is already done for us. You can download training set and test set with code that accompanies this article from here.

However before we go any further, we need to import some libraries. Here is the list of the libraries that we need to import.

As you can see we are importing Keras dependencies, NumPy and Pandas. NumPy is the fundamental package for scientific computing and Pandas provides easy to use data structures and data analysis tools.

After we imported libraries, we can proceed with importing the data and preparing it for the processing. We are going to use Pandas for importing data:

Firstly, we used read_csv function to import the dataset into local variables, and then we separated inputs (train_x, test_x) and expected outputs (train_y, test_y) creating four separate matrixes. Here is how they look like:

However, our data is not prepared for processing yet. If we take a look at our expected output values, we can notice that we have three values: 0, 1 and 2. Value 0 is used to represent Iris setosa, value 1 to represent Iris versicolor and value 2 to represent virginica. The good news about these values is that we didn’t get string values in the dataset. If you end up in that situation, you would need to use some kind of encoder so you can format data to something similar as we have in our current dataset. For this purpose, one can use LabelEncoderof sklearn library. Bad news about these values in the dataset is that they are not applicable to Sequential model. What we want to do is reshape the expected output from a vector that contains values for each class value to a matrix with a boolean for each class value. This is called one-hot encoding. In order to achieve this, we will use np_utils from the Keras library:

If you still have doubt what one-hot encoding is doing, observe image below. There are displayed train_y variable and encoding_train_y variable. Notice that first value in train_y is 2 and see the corresponding value for that row in encoding_train_y.

Once we imported and prepared the data we can create our model. We already know we need to do this by using Sequence and Dense class. So, let’s do it:

This time we are creating:

• one input layer with four nodes, because we are having four attributes in our input values
• two hidden layers with ten neurons each
• one output layer with three neurons, because we are having three output classes

In hidden layers, neurons use Rectifier activation function, while in output layer neurons use Softmax activation function (ensuring that output values are in the range of 0 and 1). After that, we compile our model, where we define our cost function and optimizer. In this instance, we will use Adam gradient descent optimization algorithm with a logarithmic cost function (called categorical_crossentropy in Keras).

Finally, we can train our network:

Artificial Neural Network Examples

And evaluate it:

If we run this code, we will get these results:

Since we have built the same network on the same dataset as we did with TensorFlow in the previous article we got the same accuracy – 0.93. That is pretty good. After this, we can call our classifier using single data and get predictions for it.

Conclusion

Neural Network Example Python

Keras is one awesome API which makes building Artificial Neural Networks easier. It is quite easy getting used to it. In this article, we just scratched the surface of this API and in next posts, we will explore how we can implement different types of Neural Networks using this API.

Thanks for reading!

This article is a part of Artificial Neural Networks Series, which you can check out here.

Neural Network C++ Code Example

Read more posts from the author at Rubik’s Code.