How Do People Lubricate润滑 Artificial Intelligence?
温馨提示：正文推送半小时，您将收到精编讲义
AI研究的主流代表
Dominant占主导地位的 Paradigms范例 of AI Research
From Moravec · 681 words · 7 mins
image
Though there is no established unifying统一 theory or paradigm范式 that guides AI research, people have taken much effort to study deep in this field, and there are several representative approaches.
Cybernetics and Brain Simulation 控制论和大脑仿真
image
In the 1940s and 1950s, a number of researchers explored the connection between neurobiology神经生物学, information theory, and cybernetics. Some of them built machines that used electronic networks to exhibit rudimentary基本的 intelligence, such as W.Grey Walter’s turtles and the Johns Hopkins Beast. Many of these researchers gathered for meetings of the Teleological Society at Princeton University and the Ratio Club in England. By 1960, this approach was largely abandoned, although elements of it would be revived in the 1980s.
Symbolic
image
Symbolic（象征的；符号的；） artificial intelligence符号人工智能 is the term for the collection of all methods in artificial intelligence research that are based on high-level “symbolic” (human-readable)（人类可读） representations of problems, logic and search. Symbolic AI was the dominant paradigm of AI research from the mid-1950s until the late 1980s.
John Haugeland gave the name GOFAI (“Good Old-Fashioned Artificial Intelligence”) to symbolic AI in his 1985 book Artificial Intelligence: The Very Idea, which explored the philosophical implications of artificial intelligence research. In robotics the analogous term is GOFR (“Good Old-Fashioned Robotics”).在机器人技术中，类似术语是“出色的老式机器人”
The approach is based on the assumption that many aspects of intelligence can be achieved by the manipulation of symbols, an assumption defined as the “physical symbol systems hypothesis” by Allen Newell and Herbert A. Simon in the middle 1960s.
The most successful form of symbolic AI is expert systems, which use a network of production rules生产规则. Production rules connect symbols in a relationship similar to an If-Then statement. The expert system processes the rules to make deductions and to determine what additional information it needs, i.e. what questions to ask, using human-readable symbols.
Sub-Symbolic
image
By the 1980s, progress in symbolic AI seemed to stall and many believed that symbolic systems would never be able to imitate all the processes of human cognition, especially perception, robotics, learning and pattern recognition. A number of researchers began to look into “sub-symbolic” approaches to specific AI problems. Sub-symbolic methods manage to approach intelligence without specific representations of knowledge. And there are two successful examples.
Firstly, embodied intelligence. This includes embodied, situated, behavior-based, and nouvelle AI. Researchers from the related field of robotics, such as Rodney Brooks, rejected symbolic AI and focused on the basic engineering problems that would allow robots to move and survive. Their work revived the non-symbolic viewpoint of the early cybernetics researchers of the 1950s and reintroduced the use of control theory in AI. This coincided with the development of the embodied mind thesis in the related field of cognitive science: the idea that aspects of the body 身体的各个方面（如运动，感知和可视化）(such as movement, perception and visualization) are required for higher intelligence.
Besides, computational intelligence and soft computing. Interest in neural networks神经网络 and “connectionism” was revived by David Rumelhart and others in the middle of the 1980s. Artificial neural networks are an example of soft computing —— they are solutions to problems which cannot be solved with complete logical certainty, and where an approximate solution is often sufficient. Other soft computing approaches to AI include fuzzy systems, evolutionary computation and many statistical tools. The application of soft computing to AI is studied collectively by the emerging discipline of computational intelligence.
Statistical Learning
image
Much of traditional GOFAI got bogged down on ad hoc patches to symbolic computation that worked on their own toy models but failed to generalize to real-world results. However, around the 1990s, AI researchers adopted sophisticated mathematical tools复杂的, such as hidden Markov models (HMM), information theory, and normative规范 Bayesian decision theory to compare or to unify competing architectures. The shared mathematical language permitted a high level of collaboration with more established fields (like mathematics, economics or operations research). The increased successes with real-world data led to increasing emphasis on comparing different approaches against shared test data to see which approach performed best in a broader context than that provided by idiosyncratic toy models特定玩具模型; AI research was becoming more scientific. Nowadays results of experiments are often rigorously measurable, and are sometimes (with difficulty) reproducible.