计算机科学概论第二版笔记,计算机科学概论原版(第九版)

《计算机科学概论原版(第九版)》由会员分享，可在线阅读，更多相关《计算机科学概论原版(第九版)(43页珍藏版)》请在人人文库网上搜索。

1、Chapter 10,Artificial Intelligence, 2007 Pearson Addison-Wesley. All rights reserved,Chapter 10: Artificial Intelligence,10.1 Intelligence and Machines 10.2 Perception 10.3 Reasoning 10.4 Additional Areas of Research 10.5 Artificial Neural Networks 10.6 Robotics 10.7 Considering the Consequences,Int。

2、elligent Agents,Agent: A “device” that responds to stimuli from its environment Sensors Actuators The goal of artificial intelligence is to build agents that behave intelligently,Levels of Intelligent Behavior,Reflex: actions are predetermined responses to the input data Intelligent response: action。

3、s affected by knowledge of the environment Goal seeking Learning,Figure 10.1 The eight-puzzle in its solved configuration,Figure 10.2 Our puzzle-solving machine,Approaches to Research in Artificial Intelligence,Performance oriented: Researcher tries to maximize the performance of the agents. Simulat。

4、ion oriented: Researcher tries to understand how the agents produce responses.,Turing Test,Proposed by Alan Turing in 1950 Benchmark for progress in artificial intelligence Test setup: Human interrogator communicates with test subject by typewriter. Test: Can the human interrogator distinguish wheth。

5、er the test subject is human or machine?,Techniques for Understanding Images,Template matching Image processing edge enhancement region finding smoothing Image analysis,Language Processing,Syntactic Analysis Semantic Analysis Contextual Analysis,Figure 10.3 A semantic net,Components of a Production 。

6、Systems,1. Collection of states Start (or initial) state Goal state (or states) 2. Collection of productions: rules or moves Each production may have preconditions 3. Control system: decides which production to apply next,Reasoning by Searching,State Graph: All states and productions Search Tree: A 。

7、record of state transitions explored while searching for a goal state Breadth-first search Depth-first search,Figure 10.4 A small portion of the eight-puzzles state graph,Figure 10.5 Deductive reasoning in the context of a production system,Figure 10.6 An unsolved eight-puzzle,Figure 10.7 A sample s。

8、earch tree,Figure 10.8 Productions stacked for later execution,Heuristic Strategies,Heuristic: A quantitative estimate of the distance to a goal Requirements for good heuristics Must be much easier to compute than a complete solution Must provide a reasonable estimate of proximity to a goal,Figure 1。

9、0.9 An unsolved eight-puzzle,Figure 10.10 An algorithm for a control system using heuristics,Figure 10.11 The beginnings of our heuristic search,Figure 10.12 The search tree after two passes,Figure 10.13 The search tree after three passes,Figure 10.14 The complete search tree formed by our heuristic。

10、 system,Handling Real-World Knowledge,Representation and storage Accessing relevant information Meta-Reasoning Closed-World Assumption Frame problem,Learning,Imitation Supervised Training Reinforcement Evolutionary Techniques,Artificial Neural Networks,Artificial Neuron Each input is multiplied by a。

11、 weighting factor. Output is 1 if sum of weighted inputs exceeds the threshold value; 0 otherwise. Network is programmed by adjusting weights using feedback from examples.,Figure 10.15 A neuron in a living biological system,Figure 10.16 The activities within a processing unit,Figure 10.17 Representa。

12、tion of a processing unit,Figure 10.18 A neural network with two different programs,Figure 10.19 An artificial neural network,Figure 10.20 Training an artificial neural network,Figure 10.20 Training an artificial neural network (continued),Figure 10.20 Training an artificial neural network (continue。

13、d),Figure 10.20 Training an artificial neural network (continued),Figure 10.21 The structure of ALVINN,Associative Memory,Associative memory: The retrieval of information relevant to the information at hand One direction of research seeks to build associative memory using neural networks that when g。

14、iven a partial pattern, transition themselves to a completed pattern.,Figure 10.22 An artificial neural network implementing an associative memory,Figure 10.23 The steps leading to a stable configuration,Robotics,Truly autonomous robots require progress in perception and reasoning. Major advances be。

15、ing made in mobility Plan development versus reactive responses Evolutionary robotics,Issues Raised by Artificial Intelligence,When should a computers decision be trusted over a humans? If a computer can do a job better than a human, when should a human do the job anyway? What would be the social impact if computer “intelligence” surpasses that of many humans。