Deduction, reasoning, problem solving
Early AI researchers developed algorithms that imitated the step-by-step reasoning that humans use when they solve puzzles or make logical deductions. By the late 1980s and '90s, AI research had also developed highly successful methods for dealing with uncertain or incomplete information, employing concepts from probability and economics.
For difficult problems, most of these algorithms can require enormous computational resources – most experience a "combinatorial explosion": the amount of memory or computer time required becomes astronomical when the problem goes beyond a certain size. The search for more efficient problem-solving algorithms is a high priority for AI research.
Human beings solve most of their problems using fast, intuitive judgments rather than the conscious, step-by-step deduction that early AI research was able to model. AI has made some progress at imitating this kind of "sub-symbolic" problem solving: embodied agent approaches emphasize the importance of sensorimotor skills to higher reasoning; neural net research attempts to simulate the structures inside human and animal brains that give rise to this skill; statistical approaches to AI mimic the probabilistic nature of the human ability to guess..
Knowledge representation
Knowledge representation and knowledge engineering are central to AI research. Many of the problems machines are expected to solve will require extensive knowledge about the world. Among the things that AI needs to represent are: objects, properties, categories and relations between objects; situations, events, states and time; causes and effects; knowledge about knowledge (what we know about what other people know); and many other, less well researched domains. A representation of "what exists" is an ontology (borrowing a word from traditional philosophy), of which the most general are called upper ontologies.
Among the most difficult problems in knowledge representation are:
- 1.Default reasoning and the qualification problem
- Many of the things people know take the form of "working assumptions." For example, if a bird comes up in conversation, people typically picture an animal that is fist sized, sings, and flies. None of these things are true about all birds. John McCarthy identified this problem in 1969 as the qualification problem: for any commonsense rule that AI researchers care to represent, there tend to be a huge number of exceptions. Almost nothing is simply true or false in the way that abstract logic requires. AI research has explored a number of solutions to this problem.
- 2.The breadth of commonsense knowledge
- The number of atomic facts that the average person knows is astronomical. Research projects that attempt to build a complete knowledge base of commonsense knowledge (e.g., Cyc) require enormous amounts of laborious ontological engineering — they must be built, by hand, one complicated concept at a time. A major goal is to have the computer understand enough concepts to be able to learn by reading from sources like the internet, and thus be able to add to its own ontology.
- 3.The subsymbolic form of some commonsense knowledge
- Much of what people know is not represented as "facts" or "statements" that they could express verbally. For example, a chess master will avoid a particular chess position because it "feels too exposed" or an art critic can take one look at a statue and instantly realize that it is a fake. These are intuitions or tendencies that are represented in the brain non-consciously and sub-symbolically. Knowledge like this informs, supports and provides a context for symbolic, conscious knowledge. As with the related problem of sub-symbolic reasoning, it is hoped thatsituated AI, computational intelligence, or statistical AI will provide ways to represent this kind of knowledge.
- Planning
- Intelligent agents must be able to set goals and achieve them. They need a way to visualize the future (they must have a representation of the state of the world and be able to make predictions about how their actions will change it) and be able to make choices that maximize the utility (or "value") of the available choices.In classical planning problems, the agent can assume that it is the only thing acting on the world and it can be certain what the consequences of its actions may be. However, if the agent is not the only actor, it must periodically ascertain whether the world matches its predictions and it must change its plan as this becomes necessary, requiring the agent to reason under uncertainty.Multi-agent planning uses the cooperation and competition of many agents to achieve a given goal. Emergent behavior such as this is used by evolutionary algorithms and swarm intelligence.
Learning
Machine learning has been central to AI research from the beginning. In 1956, at the original Dartmouth AI summer conference, Ray Solomonoff wrote a report on unsupervised probabilistic machine learning: "An Inductive Inference Machine". Unsupervised learning is the ability to find patterns in a stream of input. Supervised learning includes both classification and numerical regression. Classification is used to determine what category something belongs in, after seeing a number of examples of things from several categories. Regression is the attempt to produce a function that describes the relationship between inputs and outputs and predicts how the outputs should change as the inputs change. In reinforcement learning the agent is rewarded for good responses and punished for bad ones. These can be analyzed in terms of decision theory, using concepts like utility. The mathematical analysis of machine learning algorithms and their performance is a branch of theoretical computer science known as computational learning theory.Natural language processingNatural language processing gives machines the ability to read and understand the languages that humans speak. A sufficiently powerful natural language processing system would enable natural language user interfaces and the acquisition of knowledge directly from human-written sources, such as Internet texts. Some straightforward applications of natural language processing include information retrieval (or text mining) and machine translation.A common method of processing and extracting meaning from natural language is through semantic indexing. Increases in processing speeds and the drop in the cost of data storage makes indexing large volumes of abstractions of the users input much more efficient.Motion and manipulation
The field of robotics is closely related to AI. Intelligence is required for robots to be able to handle such tasks as object manipulation and navigation, with sub-problems of localization (knowing where you are, or finding out where other things are), mapping (learning what is around you, building a map of the environment), and motion planning (figuring out how to get there) or path planning (going from one point in space to another point, which may involve compliant motion - where the robot moves while maintaining physical contact with an object).Perception
Machine perception is the ability to use input from sensors (such as cameras, microphones, sonar and others more exotic) to deduce aspects of the world. Computer vision is the ability to analyze visual input. A few selected subproblems are speech recognition, facial recognition and object recognition.Social intelligence:Affective computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects. It is an interdisciplinary field spanning computer sciences, psychology, and cognitive science. While the origins of the field may be traced as far back as to early philosophical enquiries into emotion, the more modern branch of computer science originated with Rosalind Picard's 1995 paper on affective computing. A motivation for the research is the ability to simulate empathy. The machine should interpret the emotional state of humans and adapt its behaviour to them, giving an appropriate response for those emotions.Emotion and social skills play two roles for an intelligent agent. First, it must be able to predict the actions of others, by understanding their motives and emotional states. (This involves elements of game theory, decision theory, as well as the ability to model human emotions and the perceptual skills to detect emotions.) Also, in an effort to facilitate human-computer interaction, an intelligent machine might want to be able to display emotions—even if it does not actually experience them itself—in order to appear sensitive to the emotional dynamics of human interaction.Creativitysub-field of AI addresses creativity both theoretically (from a philosophical and psychological perspective) and practically (via specific implementations of systems that generate outputs that can be considered creative, or systems that identify and assess creativity). Related areas of computational research are Artificial intuition and Artificial imaginationGeneral intelligence
Most researchers hope that their work will eventually be incorporated into a machine with general intelligence (known as strong AI), combining all the skills above and exceeding human abilities at most or all of them. A few believe that anthropomorphic features like artificial consciousness or an artificial brain may be required for such a project.Many of the problems above are considered AI-complete: to solve one problem, you must solve them all. For example, even a straightforward, specific task like machine translation requires that the machine follow the author's argument (reason), know what is being talked about (knowledge), and faithfully reproduce the author's intention (social intelligence). Machine translation, therefore, is believed to be AI-complete: it may require strong AI to be done as well as humans can do it.A Relational approach
In "Computing Machinery and Intelligence" (1997), Turing addresses the question of which functions are essential for intelligence with a proposal for what has come to be the generally accepted test for machine intelligence. An human interrogator is connected by terminal to two subjects, one a human and the other a machine. If the interrogator fails as often as he or she succeeds in determining which is the human and which the machine, the machine could be considered as having intelligence. The Turing Test is not based on the completion of tasks or the solution of problems by the machine, but on the machine's ability to relate to a human being in conversation. Discourse is unique among human activities in that it subsumes all other activities within itself. Turing predicted that by the year 2000, there would be computers that could fool an interrogator at least thirty percent of the time. This, like most predictions in AI, was overly optimistic. No computer has yet come close to passing the Turing Test.The Turing Test uses relational discourse to demonstrate intelligence. However, Turing also notes the importance of being in relationship for the acquisition of knowledge or intelligence. He estimates that the programming of the background knowledge needed for a restricted form of the game would take at a minimum three hundred person-years to complete. This is assuming that the appropriate knowledge set could be identified at the outset. Turing suggests that rather than trying to imitate an adult mind, computer scientists should attempt to construct a mind that simulates that of a child. Such a mind, when given an appropriate education, would learn and develop into an adult mind. One AI researcher taking this approach is Rodney Brooks of the Massachusetts Institute of Technology, whose lab has constructed several robots, including Cog and Kismet, that represent a new direction in AI in which embodiedness is crucial to the robot's design. Their programming is distributed among the various physical parts; each joint has a small processor that controls movement of that joint. These processors are linked with faster processors that allow for interaction between joints and for movement of the robot as a whole. These robots are designed to learn tasks associated with human infants, such as eye-hand coordination, grasping an object, and face recognition through social interaction with a team of researchers. Although the robots have developed abilities such as tracking moving objects with the eyes or withdrawing an arm when touched, Brooks's project is too new to be assessed. It may be no more successful than Lenat's Cyc in producing a machine that could interact with humans on the level of the Turing Test. However Brooks's work represents a movement toward Turing's opinion that intelligence is socially acquired and demonstrated.The Turing Test makes no assumptions as to how the computer arrives at its answers; there need be no similarity in internal functioning between the computer and the human brain. However, an area of AI that shows some promise is that of neural networks, systems of circuitry that reproduce the patterns of neurons found in the brain. Current neural nets are limited, however. The human brain has billions of neurons and researchers have yet to understand both how these neurons are connected and how the various neurotransmitting chemicals in the brain function. Despite these limitations, neural nets have reproduced interesting behaviors in areas such as speech or image recognition, natural-language processing, and learning. Some researchers, including Hans Moravec and Raymond Kurzweil, see neural net research as a way to reverse engineer the brain. They hope that once scientists can design nets with a complexity equal to the human brain, the nets will have the same power as the brain and develop consciousness as an emergent property. Kurzweil posits that such mechanical brains, when programmed with a given person's memories and talents, could form a new path to immortality, while Moravec holds out hope that such machines might some day become our evolutionary children, capable of greater abilities than humans currently demonstrate.
No comments:
Post a Comment