Abstract
The purpose of the chapter is to provide an overview of artificial intelligence (AI) to the knowledge seekers. This chapter aims to provide the historical development of AI over the years. It provides an overview of machine learning. It talks about supervised, semi-supervised, and unsupervised, reinforcement learning, and transfer learning. It delves into the generative adversarial networks (GAN). It further provides an overview of various components of neural network (NN) such as input layers, hidden layers, output layers, forward propagation, backward propagation, training, optimization, inference, fine tuning, transfer learning, etc. The chapter will leverage academic journals, conferences, and online repositories to shed light on the dynamic landscape of AI technology.
TopIntroduction
In today’s world, technology is growing very fast, and we are getting in touch with different new technologies day by day. AI is one of the most rapidly growing technologies in computer science which is ready to create a new revolution in the world by making intelligent machines (Russell & Norvig, 2010). Artificial Intelligence is composed of two words Artificial and Intelligence, where Artificial defines “man-made” and Intelligence defines “thinking power”, hence AI means “a man-made thinking power”. In simple words, AI is a branch of computer science by which we can create intelligent machines which can behave like a human, think like a human, and able to make decisions on its own (Chandra & Hareendran, 2014; Jarrahi, 2018). With artificial Intelligence we do not need to preprogram our machines to perform certain tasks we just have to develop an algorithm that will be able to learn, understand, and perform certain task given to it on its own. In today’s world, we hardly avoid hearing about AI. We see AI in the movies, in books, in the news and online (Jarrahi, 2018). Today we use Artificial Intelligence in many different sectors such as industries, government, civil, science, etc. (Russell & Norvig, 2010; Chandra & Hareendran, 2014). For example, advanced web search engines (e.g. google search), recommendation algorithms (used by YouTube, Amazon, and Netflix), interactions via human speech (such as Google Assistant, Siri, and Alexa), self-driving cars (e.g. Tesla, Waymo), generative and creative tools (Chatgpt and AI art), and superhuman play and analysis in strategy games (such as chess and go). In simple words, AI is a method of making a computer, a computer-controlled robot, or a software think intelligently like the human mind (Mitchell, 1997).
But AI is not a new word and a new technology for researchers. This technology is much older than you would imagine. Even there are myths of Mechanical men in Ancient Greek and Egyptian Myths (Chahal & Gulia, 2019). A few milestones in the history of AI that define the journey from the AI generation to the present development are shown in Fig. 1.
Key Terms in this Chapter
Backpropagation: The gradients of the loss function with respect to the network's parameters are computed using the chain rule of calculus and propagated backward through the network, hence the term “backpropagation”.
Gradient Descent: Gradient descent (GD) is an iterative first-order optimization algorithm, used to find a local minimum/maximum of a given function. This method is commonly used in machine learning (ML) and deep learning (DL) to minimize a cost/loss function.
Stochastic Optimization: Stochastic Optimization is a method of finding the optimal solution to a problem using randomness in the search process. It is a powerful tool in machine learning and other fields, such as finance and engineering, where the goal is to optimize a function based on a set of input variables.
Neural Network: Neurons are nerve cells that send messages all over the body in a living organism. A combination of neurons or a cluster of neurons is called a neural circuit. A model based on these neural circuits in a computer or a machine is called a Neural Network.
Algorithms: A machine learning algorithm is a set of rules or processes used by an AI system to conduct tasks-most often to discover new data insights and patterns, or to predict output values from a given set of input variables.
Machine Learning: At its most fundamental level, machine learning (ML) is a category of artificial intelligence that enables computers to independently think and learn. It involves programming computers to modify their actions to improve accuracy, which is measured by the frequency of correct outcomes resulting from the chosen actions.