Introduction to Artificial Intelligence PDF

INTRODUCTION TO ARTIFICIAL INTELLIGENCE UNIT 1 ====== HISTORY OF AI ------------- ##### STUDY GOALS - Describe how artificial intelligence has developed as a scientific discipline. - understand the different paradigms of artificial intelligence winter. - explain the importance o...

INTRODUCTION TO ARTIFICIAL INTELLIGENCE UNIT 1 ====== HISTORY OF AI ------------- ##### STUDY GOALS - Describe how artificial intelligence has developed as a scientific discipline. - understand the different paradigms of artificial intelligence winter. - explain the importance of expert systems and how they have contributed to artificial intelligence. - talk about the advances of artificial intelligence. ### Introduction  ### Historical Developments - Historical views of artificial intelligence often start in the 1950s when it was first applied in computer science - The first considerations about AI were in 350 BCE #### Aristotle, Greek Philosopher (384--322 BCE) #### Leonardo da Vinci, Italian Polymath (1452--1519) #### René Descartes, French Philosopher (1596--1650) #### Thomas Hobbes, British Philosopher (1588--1679) #### David Hume, Scottish Philosopher (1711--1776) #### Recent History of Artificial Intelligence ###### Key personalities ###### Key institutions ###### Key disciplines contributing to the development of AI - In decision theory mathematical probability and economic utility are combined. This provides the formal criteria for decision-making in AI regarding economic benefit and dealing with uncertainty. - Game theory is an important foundation for rational agents to learn strategies to solve games. It is based on the research of the American--Hungarian computer scientist John von Neuman (1903--1957), and the American--German mathematician and game theorist Oskar Morgenstern (1902--1977) - Insights from neuroscience about how the brain works are increasingly used in artificial intelligence models, especially as the importance of artificial neural networks (ANN) is increasing. Nowadays, there are many models in AI trying to emulate the way the brain stores information and solves problems. - Natural language processing (NLP) combines linguistics and computer science. The goal of NLP is to process not only written language (text) but also spoken language (speech). - Lisp was developed by John McCarthy and is one of the oldest programming languages. The name comes from "list processing" as Lisp is able to process character strings in a unique way (McCarthy, 1960). Even though it dates back to the 1960s it has not only been used for early AI programming but is still relevant today. - Another early AI programming language is Prolog which was specially designed to prove theorems and solve logical formulas. - Nowadays, the general-purpose high-level programming language Python is the most important programming language. As Python is open source, there exist extensive libraries which help programmers to create applications in a very efficient way. - Increasing availability of massive amounts of data, which are required to develop and train AI algorithms. - Large improvements in data processing capacity of computers. - New insights from mathematics, cognitive science, philosophy, and machine learning. ### AI Winter #### The First AI Winter (1974--1980) #### The Second AI Winter (1987--1993) #### Causes of the AI Winters - algorithms and experience with them, - computing capacity, and - the availability of data. #### The Next AI Winter  ### Expert Systems - Expert systems belong to the group of knowledge-based systems. - The goal of expert systems is to emulate the decision and solution-finding process using the domain-specific knowledge of an expert. - The word "expert" refers to a human with specialized experience and knowledge in a given field - Since problems in any given domain may be like each other, but never quite alike, solving problems in that domain cannot be accomplished by memorization alone. Rather, problem-solving is supplemented by a method that involves matching or applying experiential knowledge to new problems and application scenarios. #### Components of an Expert System #### Types of Expert Systems - Case-based systems store examples of concrete problems together with a successful solution. When presented with a novel, previously unseen case, the system tries to retrieve a solution to a similar case and apply this solution to the case at hand. The key challenge is defining a suitable similarity measure to compare problem settings. - Rule-based systems represent the knowledge base in the form of facts and if-A-then-B- type rules that describe relations between facts. - If the problem class to be solved can be categorized as a decision problem, the knowledge can be represented in a decision tree. The latter are typically generated by analyzing a set of examples. #### Development of Expert Systems 1. Firstly, the computational complexity of inference grows faster than it does linearly in the number of facts and rules. This means that for many practical problems the system's answering times were prohibitively high. 2. Secondly, as a knowledge base grows, proving its consistency by ensuring that no constituent parts contradict each other becomes exceedingly challenging. ### Notable Advances #### Nascent Artificial Intelligence (1956--1974) #### Knowledge Representation (1980--1987) #### Learning from Data (Since 1993) #### Adjacent Fields of Study ###### Linguistics ###### Cognition ###### Games ###### The Internet of Things ###### Quantum computing #### The Future of AI 1. In the discovery phase a technological trigger or breakthrough generates significant interest and triggers the innovation. 2. The peak phase of exaggerated expectations is usually accompanied by much enthusiasm. Even though there may be successful applications most of them struggle with early problems. 3. The period of disillusionment shows that not all expectations can be met. 4. In the period of enlightenment, the value of innovation is recognized. There is an understanding of the practical understanding and advantages, but also of the limitations of the new technology. 5. In the last period, a plateau of productivity is reached, and the new technology becomes the norm. The final level of this plateau depends on whether the technology is adopted in a niche or a mass market.  - In the innovation trigger phase, subjects like composite AI (a combination of different approaches from AI) and general AI (the ability of a machine to perform humanlike intellectual tasks) appear. Moreover, topics like Human-Centered AI and Responsible AI show that human integration is becoming increasingly important for the future of AI. - Deep neural networks, which have been the driver for new levels of performance in many machine learning applications over the past decades, are still at the peak phase of inflated expectations or hype. Moreover, topics like knowledge graphs and smart robots appear in that phase. - In the disillusionment phase, we find topics like autonomous vehicles, which have experienced defunding as the high expectations in this area could not be met.