Chapter 1, Neural Network and Artificial Intelligence Concepts, introduces the basic theoretical concepts of Artificial Neural Networks (ANN) and Artificial Intelligence (AI). It presents the simple applications of ANN and AI with usage of math concepts. Some introduction to R ANN functions is also covered.
Chapter 2, Learning Processes in Neural Networks, shows how to do exact inferences in graphical models and show applications as expert systems. Inference algorithms are the base components for learning and using these types of models. The reader must at least understand their use and a bit about how they work.
Chapter 3, Deep Learning Using Multilayer Neural Networks, is about understanding deep learning and neural network usage in deep learning. It goes through the details of the implementation using R packages. It covers the many hidden layers set up for deep learning and uses practical datasets to help understand the implementation.
Chapter 4, Perceptron Neural Network – Basic Models, helps understand what a perceptron is and the applications that can be built using it. This chapter covers an implementation of perceptrons using R.
Chapter 5, Training and Visualizing a Neural Network in R, covers another example of training a neural network with a dataset. It also gives a better understanding of neural networks with a graphical representation of input, hidden, and output layers using the plot() function in R.
Chapter 6, Recurrent and Convolutional Neural Networks, introduces Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) with their implementation in R. Several examples are proposed to understand the basic concepts.
Chapter 7, Use Cases of Neural Networks – Advanced Topics, presents neural network applications from different fields and how neural networks can be used in the AI world. This will help the reader understand the practical usage of neural network algorithms. The reader can enhance his or her skills further by taking different datasets and running the R code.
