Foundations of Artificial Intelligence Based Systems

Artificial intelligence (AI) has been at the forefront of technology over the last few years, and has made its way into mainstream applications, such as expert systems, personalized applications on mobile devices, machine translation in natural language processing, chatbots, self-driving cars, and so on. The definition of AI, however, has been a subject of dispute for quite a while. This is primarily because of the so-called AI effect that categorizes work that has already been solved through AI in the past as non-AI. According to a famous computer scientist:

Building an intelligent system that could play chess was considered AI until the IBM computer Deep Blue defeated Gary Kasparov in 1996. Similarly, problems dealing with vision, speech, and natural language were once considered complex, but due to the AI effect, they would now only be considered computation rather than true AI. Recently, AI has become able to solve complex mathematical problems, compose music, and create abstract paintings, and these capabilities of AI are ever increasing. The point in the future at which AI systems will equal human levels of intelligence has been referred to by scientists as the AI singularity. The question of whether machines will ever actually reach human levels of intelligence is very intriguing. 

Many would argue that machines will never reach human levels of intelligence, since the AI logic by which they learn or perform intelligent tasks is programmed by humans, and they lack the consciousness and self-awareness that humans possess. However, several researchers have proposed the alternative idea that human consciousness and self-awareness are like infinite loop programs that learn from their surroundings through feedback. Hence, it may be possible to program consciousness and self-awareness into machines, too. For now, however, we will leave this philosophical side of AI for another day, and will simply discuss AI as we know it.

Put simply, AI can be defined as the ability of a machine (generally, a computer or robot) to perform tasks with human-like intelligence, possessing such as attributes the ability to reason, learn from experience, generalize, decipher meanings, and possess visual perception. We will stick to this more practical definition rather than looking at the philosophical connotations raised by the AI effect and the prospect of the AI singularity. While there may be debates about what AI can achieve and what it cannot, recent success stories of AI-based systems have been overwhelming. A few of the more recent mainstream applications of AI are depicted in the following diagram:

This book will cover the detailed implementation of projects from all of the core disciplines of AI, outlined as follows:

• Transfer learning based AI systems
• Natural language based AI systems
• Generative adversarial network (GAN) based applications
• Expert systems
• Video-to-text translation applications
• AI-based recommender systems
• AI-based mobile applications
• AI-based chatbots
• Reinforcement learning applications

In this chapter, we will briefly touch upon the concepts involving machine learning and deep learning that will be required to implement the projects that will be covered in the following chapters.