Artificial intelligence (AI) is the intelligence of machines and the branch of computer science that aims to create it.
Textbooks define the field as "the study and design of intelligent agents," where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success
• 2 Problems
o 2.1 Deduction, reasoning, problem solving
o 2.2 Knowledge reprentation
o 2.3 Planning
o 2.4 Learning
topiao 2.5 Natural language processing
o 2.6 Motion and manipulation
大学英语四六级报名
o 2.7 Perception四级论坛
o 2.8 Social intelligence
o 2.9 Creativity
o 2.10 General intelligence
• 3 Approaches
o 3.1 Cybernetics and brain simulation
o 3.2 Symbolic
o 3.3 Sub-symbolic
o 3.4 Statistical
o 3.5 Integrating the approaches
• 4 Tools
o 4.1 Search and optimization
播弄
o 4.2 Logic
o 4.3 Probabilistic methods for uncertain reasoning
英语4级考试时间
o 4.4 Classifiers and statistical learning methods
o 4.5 Neural networks
o 4.6 Control theory
o 4.7 Languages
• 5 Evaluating progress
• 6 Applications
gaterpillar
o 6.1 Competitions and prizes
o 6.2 Platforms
•7 Philosophy
•8 Prediction
Deduction, reasoning, problem solving
Early AI rearchers developed algorithms that imitated the step-by-step reasoning tho humans were often assumed to u when they solve puzzles play board games or make logical deductions.
By the late 1980s and '90s, AI rearch had also developed highly successful methods for dealing with uncertain or incomplete information, employing concepts from probability and economics.
For difficult problems, most of the 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 arch for more efficient problem solving algorithms is a high priority for AI rearch.
Human beings solve most of their problems using fast, intuitive judgments rather than the conscious, step-by-step deduction that early AI rearch 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 nsorimotor skills to higher reasoning;
Neural net rearch attempts to simulate the structures inside human and animal brains that give ri to this skill.
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 the things are true about all birds. John McCarthy identified this problem in 1969 as the
qualification problem: for any commonn rule that AI rearchers care to reprent, there tend to be a huge number of exceptions. Almost nothing is simply true or fal in the way that abstract logic requires.
AI rearch has explored a number of solutions to this problem.[51]
The breadth of commonn knowledge
The number of atomic facts that the average person knows is astronomical.
Rearch projects that attempt to build a complete knowledge ba of commonn
knowledge (e.g., Cyc) require enormous amounts of laborious ontological engineering— they must be built, by hand, one complicated concept at a time.[52] 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.
The sub symbolic form of some commonn knowledge
Much of what people know is not reprented as "facts" or "statements" that they could actually say out loud. For example, a chess master will avoid a particular chess position becau it "feels too expod" or an art critic can take one look at a statue and instantly realize that it is a fake.[54] The are intuitions or tendencies that are reprented in the brain non-consciously and sub-symbolically.[55] 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 that situated AI or computational intelligence will provide ways to reprent this kind of knowledge.]
Planning
Main article: Automated planning and scheduling
Learning
Main article: Machine learning
Natural language processing
ASIMO us nsors and intelligent algorithms to avoid obstacles and navigate stairs.
四级阅读理解技巧Main article: Natural language processing
Natural language processing [64] gives machines the ability to read and understand the languages that humans speak. Many rearchers 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.[65]
Motion and manipulation
Main article: Robotics
The field of robotics[66] is cloly related to AI. Intelligence is required for robots to be able to handle such tasks as object manipulation[67] 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).[68] Perception
Main articles: Machine perception, Computer vision, and Speech recognition
Machine perception[69] is the ability to u input from nsors (such as cameras, microphones, sonar and others more exotic) to deduce aspects of the world.Computer vision[70] is the ability to analyze visual input.
english jokeA few lected subproblems are speech recognition,[71]facial recognition and object recognition.[72] Social intelligence
Main article: Affective computing
Kismet, a robot with rudimentary social skills
Emotion and social skills[73] 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 o
f game theory, decision theory, as well as the ability to model human emotions and the perceptual skills to detect emotions.) Also, for good human-computer interaction, an intelligent machine also needs
vitamindto display emotions. At the very least it must appear polite and nsitive to the humans it interacts with. At best, it should have normal emotions itlf.
Creativity
Main article: Computational creativity
TOPIO, a robot that can play table tennis, developed by TOSY.
A sub-field of AI address creativity both theoretically (from a philosophical and psychological perspective) and practically (via specific implementations of systems that generate outputs that can be considered creative). A related area of computational rearch is Artificial Intuition and Artificial Imagination.
General intelligence
Main articles: Strong AI and AI-complete
Most rearchers 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.[12] A few believe that anthropomorphic features like artificial consciousness or an artificial brain may be required for such a project.[74]
billowMany 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.[75]
Approaches
There is no established unifying theory or paradigm that guides AI rearch. Rearchers disagree about many issues.[76] A few of the most long standing questions that have remained unanswered are the: should artificial intelligence simulate natural intelligence, by studying psychology or neurology? Or is human biology as irrelevant to AI rearch as bird biology is to aeronautical engineering?[77] Can intelligent behavior be described using simple, elegant principles (such as logi
c or optimization)? Or does it necessarily require solving a large number of completely unrelated problems?[78] Can intelligence be reproduced using high-level symbols, similar to words and ideas? Or does it require "sub-symbolic" processing?[79]
