In the world of computers, artificial intelligence is the ability of an electronic device or computer program to use its brain or intelligence to perform different kind of tasks; for example, in the binary world, a computer program may use its artificial intelligence and neural networks to analyze the environment, learn from the environment, and perform a particular task.
As you can see, this is a diagram that an individual can use to understand some of the differences between artificial intelligence and its subfields:
Artificial Intelligence: As previously stated, artificial intelligence (AI) is the ability of an electronic device or computer program to use its brain and intelligence to perform some operations. For example, in software development, when an individual is interacting or chating with a computer program, a computer program can use some conditional statements to evaluate the user input and respond logically to that user, imitating the brain or intelligence of a human being. In the computers world, this imitation is known as artificial intelligence. In addition to that kind of artificial intelligence, there are other kinds of AI, such as machine learning and deep learning. In those subsets of AI, we can say that a computer application is using AI when it is using machine learning features or deep learning features.
Machine Learning: Machine learning (ML) is a subset of artificial intelligence where a computer program can improve itself with time and experience.
Deep Learning: Deep learning (DL) is a subset of machine learning where a computer program can use advanced neural networks to train and improve itself.
In an electronic device or computer application, an artificial neural network (ANN) is similar to the neural network of a human brain, and it is composed by a group of neurons, which will have several inputs and one output. As you can see, those are some of the most important artificial neural networks (ANNs) that an electronic device or a computer application can use to perform its operations:
-Feedforward Neural Networks: In the brain of an electronic device or computer program, when the information is moving directly in one direction among the neurons or nodes of its brain, the agent has a feedforward neural network inside of its brain. To put it another way, an agent will have a feedforward neural network on its brain when the information is moving in one direction among its neurons and without doing circles among nodes.
-Recurrent Neural Networks: The term recurrent neural network (RNN) is derived from another artificial intelligence term that is known as feedforward neural network. In this case, an agent will have a recurrent neural network on its brain when the information is moving in loops among its neurons or nodes to be able to store and remember data from previous experiences.
-Convolutional Neural Networks: A convolutional neural network (CNN) is a deep learning term that is used for those neural networks that are using convolution, which is a mathematical operation where two different kinds of functions can produce a third function. In deep learning, an electronic device or computer program can use its convolutional neural network (CNN) for image recognition, image classification, natural language processing (NLP), and other deep learning tasks.
In the field of machine learning, there is a concept that is called reinforcement learning, also known as RL. What is reinforcement learning? It is an ability of trial and error that an agent is going to use to learn from an unknown environment. While a computer application is learning from an unknown environment, this agent will have the notion of rewards and penalties to be able to learn from the environment and improve its ability to perform a better action in the future.
In this book, an individual will learn how to use his/her programming skills to develop different kinds of trading apps, such as those machine learning apps that will extract data from the Security and Exchanges Commission (SEC) to perform fundamental and technical analysis of the financial statements of a company. More specifically, in this book, a coder will learn how to download the balance-sheet and income-statement from the SEC and build a ML app that will analyze those financial statements.
In the last chapters of this book, a coder will build different kinds of neural networks that will analyze a group of shares; furthermore, a programmer is going to learn some techniques related to deep learning and reinforcement learning.
Principles of Biomedical Engineering by Sundararajan V. Madihally: If you are a programmer who doesn’t know anything about biomedical engineering and want to start building biomedical engineering apps, “Principles of Biomedical Engineering” is a good point to start learning the basics. Even through this book will not teach you how to develop source codes, it will give you that kind of knowledge that a coder can use with other books to develop biomedical engineering apps. To put it another way, Principles of Biomedical Engineering is not a “practical book of the real world”, it is a “theoretical book” that will give you a general overview of biomedical engineering (BE); then, after having a general idea of this field of study and learning some of the most important points of biomedical engineering (BE), you can choose another book to go deeper in a specific point. In other words, as an example, in this book, you will learn the theory and basics of cellular engineering, biofluid flow, biosensors, biomedical imaging, and other BE topics; then, if you want to develop biomedical imaging apps, you can choose a practical book that can go deeper in biomedical imaging and can show you real world examples that will focus more in practice rather than theory.
Deep Learning for Data Analytics by Himansu Das: If you know the basics of biomedical engineering, software development, and artificial intelligence, you can read this book and learn some deep learning techniques that an individual can apply to a section of biomedical engineering that is known as biomedical imaging. Shortly, in this book, a coder will learn about deep learning algorithms that can extract complex information from medical images, such as those medical images that an individual can obtain from a MRI, CT-Scan, or X-Ray; then, after extracting those medical images, the deep learning algorithms will process and analyze the data of those images to find solutions to real-life problems.