Description |
1 online resource |
|
text file |
|
PDF |
Note |
Includes index. |
Summary |
"Learn the core concepts of neural networks and discover the different types of neural network, using Unity as your platform. In this book you will start by exploring back propagation and unsupervised neural networks with Unity and C#. You'll then move onto activation functions, such as sigmoid functions, step functions, and so on. The author also explains all the variations of neural networks such as feed forward, recurrent, and radial. Once you've gained the basics, you'll start programming Unity with C#. In this section the author discusses constructing neural networks for unsupervised learning, representing a neural network in terms of data structures in C#, and replicating a neural network in Unity as a simulation. Finally, you'll define back propagation with Unity C#, before compiling your project. What You'll LearnDiscover the concepts behind neural networksWork with Unity and C#See the difference between fully connected and convolutional neural networksMaster neural network processing for Windows 10 UWPWho This Book Is ForGaming professionals, machine learning and deep learning enthusiasts."-- Provided by publisher |
Contents |
Intro; Table of Contents; About the Authors; About the Technical Reviewer; Introduction; Chapter 1: Neural Network Basics; Introducing Neural Networks; Digging Deeper into Neural Networks; Perceptron; Activation Function and Its Different Types; Identity Function; Binary Step Function; Logistic or Sigmoid; Tan H Function; Arctan Function; Rectified Linear Unit; Leaky ReLU; Softmax Function; Biases and Weights; Neural Network from Scratch; Backpropagation; Summary; Chapter 2: Unity ML-Agents; Unity IDE; Getting Started with Machine Learning Agents; Let's Start with TensorFlow |
|
Understanding AnacondaWhat Is the NVDIA CUDA Toolkit?; GPU-Accelerated TensorFlow; Building aProject inUnity; Internal Operations forMachine Learning; Training Anaconda inPython Mode; Working with Jupyter Notebook; Proximity Policy Optimization; Summary; Chapter 3: Machine Learning Agents and Neural Network inUnity; Extending the Unity ML-Agents with Further Examples; Crawler Project; Testing the Simulation; Neural Network with Unity C#; Creating DataStructures; Experimenting withtheSpider Asset; Summary; Chapter 4: Backpropagation inUnity C#; Going Further into Backpropagation |
|
Backpropogation inUnity C#Constructing Data Structures; Feed Forwarding and Initializing Weights; Testing of Backpropagation Neural Network; Summary; Chapter 5: Data Visualization inUnity; Machine Learning Data Visualization inUnity; Data Parsing; Working with Datasets; Another Example; Summary; Index |
Subject |
Unity (Electronic resource)
|
|
Unity (Electronic resource) |
|
Neural networks (Computer science) -- Computer programs.
|
|
C# (Computer program language)
|
|
Réseaux neuronaux (Informatique) -- Logiciels. |
|
C# (Langage de programmation) |
|
Microsoft programming. |
|
Games development & programming. |
|
C# (Computer program language) |
Added Author |
Biswas, Manisha, author.
|
Other Form: |
Print version: Nandy, Abhishek. Neural Networks in Unity. California : Apress, [2018] 1484236726 9781484236727 (OCoLC)1030906652 |
ISBN |
9781484236734 (electronic bk.) |
|
1484236734 (electronic bk.) |
Standard No. |
10.1007/978-1-4842-3673-4 doi |
|