《人工智能复习版》由会员分享，可在线阅读，更多相关《人工智能复习版（13页珍藏版）》请在金锄头文库上搜索。
1、|人工智能复习指南一、术语解释|I、人工智能 artificial intelligence4、产生式规贝 production rules6、后项链接 backward chaining9、排中律 law of the excluded middle 10、贝叶斯推理 Bayesian reasoningII、确定因子 certainty factors141719212326283032342、知识 knowledge3、专家系统 expert system5、前向链接 forward chaining7、冲突 conflict8、推理引擎 inference engine12、模糊集 f
2、uzzy set 13、模糊逻辑 fuzzy logic 15、模糊限制语hedge 16、模糊规贝0 fuzzy rule 18、模糊关联记忆 fuzzy associative memory 20、隶属函数 membership function 22、人工神经网络 artificial neural networks语言变量 linguistic variable 模糊推理 fuzzy inference 质心技术 centroid technique 单态模式singleton 神经元 neuron 24、权重 weight 25、符号激活函数 sign activation func
3、tion感知器 perceptron27、线性分割函数 linear separable function超平面 hyper plane29、向后传送 back-propagation硬限幅函数 hard-limit function 31、阶跃函数 step function 多层神经网络 multilayer neural networks33、隐含层 hidden layer自反馈 self-feedback35、循环神经网络 recurrent neural network36、双向相关记忆 bidirectional associative memory 37、监督学习 superv
4、ised learning38、无监督学习unsupervised learning 39、竞争学习 competitive learning40、自组织神经网络 self-organizing neural networks 41、存储模式对 store pattern pairs42、基本记忆 fundamental memory43、自组织特征映射 self-organizing feature map44、进化计算 evolutionary computation 45、遗传算法 genetic algorithms47、基因 gene 48、进化策略 evolution strate
5、gy 50、突变操作 mutation operator52、性能图 performance graph54、秩 rank46、染色体 chromosome4951、53、55、56、遗传编程 genetic programming 交叉操作 crossover operator 模式定理 schema theorem 链表处理语言 linked list processing language知识工程 knowledge engineering58、原型prototype59、测试用例 test case57、数据挖掘 data mining60、系统维护 system maintenanc
6、e二、简述第1章1、图灵测试内容。(网上总结的)A man without the knowledge of the condition is through a special way, with a machine to answer questions. If in a quite long time, he could not tell the difference between the object of communicate with him is people or machines, then this machine can be considered to thinki
7、ng. This is the famous Turing test.2、智能的定义。(P2)Intelligence is their ability to understand and learn things.Intelligence is the ability to think and understand instead of doing things by instinctor automatically.3、人工智能的定义。（P18加点第二段）Artificial intelligence is a science that make machines do things th
8、at would require intelligence if done by humans.第2章4、什么是产生式规则及其组成？（P26、P26 2.2）（ 1 ） These statements represented in the IF-THEN form are called production rules.（ 2） Any rule consists of two parts: the IF part, called the antecedent （premise or condition） and the THEN part called the consequent （co
9、nclusion or action）.Explanation FacilitiesUser Interface专家系统的基本结构5、描述前向链接和后向链接推理技术。（1）Forward chaining is the data-driven reasoning. The reasoning starts from the known data and proceeds forward with that data. Each time only the topmost rule is executed. When fired, the rule adds a new fact in the
10、database. Any rule can be executed only once. The match-fire cycle stops when no further rules can be fired.（ P37）MatchFireKnowledge BaseMatchFireMatchFifeMatchF 雇Knowledge Bas-77)ZFCT 皿 WCycle 2Cdyclc 3(P38)AJV誉吕心去i F-C! f XCL MCcle 1(2) Backward chaining is the goal-driven reasoning. In backward c
11、haining, an expert system has the goal (a hypo theti cal solutand the inference engine attempts to find the evidence to prove it. First, the knowledge base is searched to find rules that might have the desired solution. Such rules must have the goal in their THEN (action) parts. If such a rule is fo
12、und and its IF (condition) part matches data in the database, thenthe rule is fired and the goal is proved. (P38)Pass 4FIyqKnovdedge BasePass 5FIyqPass 6Knowledge BaseM Y&DZ 1-3 AXL AfNKnovdedge BaseL&DZ X&丹&占一 FC*Stib-GMi: KPass 2Sub-GMl: XPass 1Pass 3Y&DZA-XDatabaseDatabaseKhovtied-ge BaseKnowledg
13、e BaseKhowled-ge BaseF&Z)X&Ef YIA-Xax Q1C11一订|L &Af f 时|LISub-Gaol: YSub-Goal: XX&B &EYGoa: Z(P39)第三章6、贝叶斯推理、确定因子技术的定义区别及适用情况。(1)(P62)p(Eh 卜 ph)pEHKPWpEzHFPFH)(2) Certainty factor is a number to measure the experts belief. The maximum value of the certainty factor is, say, +1.0 (definitely true) and
14、 the minimum -1.0(definitely false). A position value represented a degree of belief and a negative a degree of disbelief.(P74 3.6 中间)(3) Certainty factors are used 讦 the probabilities are not known or cannot be easilyobtains. （P84 最后一段）7、模糊集、模糊推理、模糊逻辑、隶属函数的定义。DOA fuzzy set is a set with fuzzySpSetSaries. （P91 下面）M（m2b）rFhpzy inference can be defined as a process of mapping from a given input to an output, using the theory of fuzzy sets. （P106 4.6）0.（3）FUzZyhlOgjc was introdAvedageJan Lukasiewicz iTahe 1920s. FUzzy logic is a se0cf mathematical principles for knowledge representation base
