The term Artificial Intelligence (AI) was first used by John McCarthy who considers it to mean "the science and engineering of making intelligent machines". It can also refer to intelligence as exhibited by an artificial (man-made, non-natural, manufactured) entity. The terms strong and weak AI can be used to narrow the definition for classifying such systems. AI is studied in overlapping fields of computer science, psychology, neuroscience and engineering, dealing with intelligent behavior, learning and adaptation and usually developed using customized machines or computers.

Research in AI is concerned with producing machines to automate tasks requiring intelligent behavior. Examples include control, planning and scheduling, the ability to answer diagnostic and consumer questions, handwriting, natural language, speech and facial recognition. As such, the study of AI has also become an engineering discipline, focused on providing solutions to real life problems, knowledge mining, software applications, strategy games like computer chess and other video games. One of the biggest difficulties with AI is that of comprehension. Many devices have been created that can do amazing things, but critics of AI claim that no actual comprehension by the AI machine has taken place.

History

The field of artificial intelligence truly dawned in the 1950s, since then there have been many achievements in the History of artificial intelligence, some of the more notable moments include:

During the 1970s and 1980s AI development experienced an AI winter due to failure to achieve expectations and lack of governmental funding.

During the 1990s and 2000s AI has become very influenced by probability theory and statistics. Bayesian networks are the focus of this movement, providing links to more rigorous topics in statistics and engineering such as Markov models and Kalman filters, and bridging the divide between 'neat' and 'scruffy' approaches. This new school of AI is sometimes called 'machine learning'. The last few years have also seen a big interest in game theory applied to AI decision making. After the September 11, 2001 attacks there has been much renewed interest and funding for threat-detection AI systems, including machine vision research and data-mining.

Mechanisms

Generally speaking AI systems are built around automated inference engines. Based on certain conditions ("if") the system infers certain consequences ("then"). AI applications are generally divided into two types, in terms of consequences: classifiers ("if shiny then diamond") and controllers ("if shiny then pick up"). Controllers do however also classify conditions before inferring actions and therefore classification form a central part of most AI systems.

Classifiers make use of pattern recognition for condition matching. In many cases this does not imply absolute, but rather the closest match. Techniques to achieve this divides roughly into two schools of thought: Conventional AI and Computational intelligence (CI)

Classifiers

Classifiers are functions that can be tuned according to examples, making them very attractive for use in AI. These examples are known as observations or patterns. In supervised learning, each pattern belongs to a certain predefined class. A class can be seen as a decision that has to be made. All the observations combined with their class labels are known as a data set.

When a new observation is received, the observation is classified based on previous experience. A classifier can be trained in various ways, there are mainly statistical and machine learning approaches.

A wide range of classifiers are available, each with its strengths and weaknesses. Classifier performance depends greatly on the characteristics of the data to be classified. There is no single classifier that works best on all given problems, this is also referred to as the 'No free lunch theorem'. Various empirical tests have been performed to compare classifier performance and to find the characteristics of data that determine classifier performance. Determining a suitable classifier for a given problem is however still more an art than science.

The most widely used classifiers are the neural network (multi-layer perceptron), support vector machines, k-nearest neighbors, Gaussian mixture model, Gaussian, naive Bayes, decision trees and radial basis functions. Van der Walt and Barnard investigated very specific artificial data sets to determine conditions under which certain classifiers perform better and worse than others.

Conventional AI

Conventional AI mostly involves methods now classified as machine learning, characterized by formalism and statistical analysis. This is also known as symbolic AI, logical AI, neat AI and Good Old Fashioned Artificial Intelligence (GOFAI). (Also see semantics.) Methods include:

• Expert systems: apply reasoning capabilities to reach a conclusion. An expert system can process large amounts of known information and provide conclusions based on them.
• Case based reasoning: stores a set of problems and answers in an organized data structure called cases. A Case Based Reasoning system upon being presented with a problem finds a case in its knowledge base that is most closely related to the new problem and presents its solutions as an output with suitable modifications.
• Bayesian networks
• Behavior based AI: a modular method building AI systems by hand.

Computational intelligence

Computational intelligence involves iterative development or learning (e.g. parameter tuning e.g. in connectionist systems). Learning is based on empirical data and is associated with non-symbolic AI, scruffy AI and soft computing. Methods mainly include:

• Neural networks: systems with very strong pattern recognition capabilities.
• Fuzzy systems: techniques for reasoning under uncertainty, have been widely used in modern industrial and consumer product control systems.
• Evolutionary computation: applies biologically inspired concepts such as populations, mutation and survival of the fittest to generate increasingly better solutions to the problem. These methods most notably divide into evolutionary algorithms (e.g. genetic algorithms) and swarm intelligence (e.g. ant algorithms).

With hybrid intelligent systems attempts are made to combine these two groups. Expert inference rules can be generated through neural network or production rules from statistical learning such as in ACT-R. It is thought that the human brain uses multiple techniques to both formulate and cross-check results. Thus, systems integration is seen as promising and perhaps necessary for true AI.

Research challenges

The DARPA Grand Challenge is a race for a $2 million prize where cars drive themselves across several hundred miles of challenging desert terrain without any communication with humans, using GPS, computers and a sophisticated array of sensors. In 2005 the winning vehicles completed all 132 miles of the course in just under 7 hours.

A popular challenge amongst AI research groups is the RoboCup and FIRA annual international robot soccer competitions.

In the post-dot com boom era, some search engine websites have sprung using a simple form of AI to provide answers to questions entered by the visitor. Questions such as "What is the tallest building?" can be entered into the search engine's input form and a list of answers will be returned.