AI research

Problems of AI

While there is no universally accepted definition of intelligence,^[50] AI researchers have studied several traits that are considered essential.^[5]

Deduction, reasoning, problem solving

Early AI researchers developed algorithms that imitated the process of conscious, step-by-step reasoning that human beings use when they solve puzzles, play board games, or make logical deductions.^[51] By the late 80s and 90s, AI research had also developed highly successful methods for dealing with uncertain or incomplete information, employing concepts from probability and economics.^[52]

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.^[53]

It is not clear, however, that conscious human reasoning is any more efficient when faced with a difficult abstract problem. Cognitive scientists have demonstrated that human beings solve most of their problems using unconscious reasoning, rather than the conscious, step-by-step deduction that early AI research was able to model.^[54] Embodied cognitive science argues that unconscious sensorimotor skills are essential to our problem solving abilities. It is hoped that sub-symbolic methods, like computational intelligence and situated AI, will be able to model these instinctive skills. The problem of unconscious problem solving, which forms part of our commonsense reasoning, is largely unsolved^{[dubious – discuss]}.

Knowledge representation

Knowledge representation^[55] and knowledge engineering^[56] 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;^[57] situations, events, states and time;^[58] causes and effects;^[59] knowledge about knowledge (what we know about what other people know);^[60] and many other, less well researched domains. A complete representation of "what exists" is an ontology^[61] (borrowing a word from traditional philosophy), of which the most general are called upper ontologies.

Among the most difficult problems in knowledge representation are:

• 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 birds in general. John McCarthy identified this problem in 1969^[62] 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.^[63]
• Unconscious knowledge: Much of what people know isn't represented as "facts" or "statements" that they could actually say out loud. They take the form of intuitions or tendencies and are represented in the brain unconsciously and sub-symbolically. This unconscious knowledge informs, supports and provides a context for our conscious knowledge. As with the related problem of unconscious reasoning, it is hoped that situated AI or computational intelligence will provide ways to represent this kind of knowledge.
• The breadth of common sense 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, such as Cyc, require enormous amounts of tedious step-by-step ontological engineering — they must be built, by hand, one complicated concept at a time.^[64]

Planning

Intelligent agents must be able to set goals and achieve them.^[65] 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. They must also attempt to determine the utility or "value" of the choices available to it.^[66]

In some 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.^[67] However, if this is not true, it must periodically check if the world matches its predictions and it must change its plan as this becomes necessary, requiring the agent to reason under uncertainty.^[68]

Multi-agent planning tries to determine the best plan for a community of agents, using cooperation and competition to achieve a given goal. Emergent behavior such as this is used by both evolutionary algorithms and swarm intelligence.^[69]

Learning

Important machine learning^[70] problems are:

• Unsupervised learning: find a model that matches a stream of input "experiences", and be able to predict what new "experiences" to expect.
• Supervised learning, such as classification (be able to determine what category something belongs in, after seeing a number of examples of things from each category), or regression (given a set of numerical input/output examples, discover a continuous function that would generate the outputs from the inputs).
• Reinforcement learning:^[71]the agent is rewarded for good responses and punished for bad ones. (These can be analyzed in terms 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 processing

Natural language processing^[72] gives machines the ability to read and understand the languages human beings speak. Many researchers hope that a sufficiently powerful natural language processing system would be able to acquire knowledge on its own, by reading the existing text available over the internet. Some straightforward applications of natural language processing include information retrieval (or text mining) and machine translation.^[73]

Motion and manipulation

ASIMO uses sensors and intelligent algorithms to avoid obstacles and navigate stairs.

Main article: robotics

The field of robotics^[74] is closely related to AI. Intelligence is required for robots to be able to handle such tasks as object manipulation^[75] and navigation, with sub-problems of localization (knowing where you are), mapping (learning what is around you) and motion planning (figuring out how to get there).^[76]

Perception

Machine perception^[77] 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^[78] is the ability to analyze visual input. A few selected subproblems are speech recognition,^[79] facial recognition and object recognition.^[80]

Social intelligence

Kismet, a robot with rudimentary social skills.

Emotion and social skills play two roles for an intelligent agent:^[81]

• 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.)
• For good human-computer interaction, an intelligent machine also needs to display emotions — at the very least it must appear polite and sensitive to the humans it interacts with. At best, it should appear to have normal emotions itself.

Creativity

A sub-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).