Published on October 13, 2009
artificial intelligence Presented by:- Saket kr Pathak M.Sc. Nt & M Amity institute of info. Tech. : artificial intelligence Presented by:- Saket kr Pathak M.Sc. Nt & M Amity institute of info. Tech. Basic Introduction : Basic Introduction System that thinks like “Human”. System that think “Rationally”. System that acts like “Humans”. System that acts “Rationally”. E.g. Micine:- Identifies bacterial infection as “Bacteremia” and recommends “Antibiotics”. Dendral:- Helps Organic Chemists to identifying “Unknown Organic Molecules” by analyzing their “Mass Spectrum” and “General Theoretical Approach of Chemistry” . System that thinks like Humans : System that thinks like Humans How do Human think ? This part is concern to the Scientific theory of internal Brain and its Activity, as Level of Abstraction, Knowledge and Circuitry. Cognitive Science. Cognitive Neuroscience. System that thinks Rationally : System that thinks Rationally Capturing the Laws of Thought Aristotle:- Identifying “Correct Argument” and “Thought Processes”. Correctness depends upon irrefutability of reasoning process. Concern study initiates the fields of Logic. The Log cist tradition in AI tries to create “Intelligent Systems Using Logic Programming”. System that acts like Humans : System that acts like Humans A few test that satisfies System’s Behavior as “Intelligence” Operation Test for Intelligence i.e. Computer Games Turing Computing Machinery and Intelligence. Test for Relevance or Relativity Tests. Collaborative Test of major Components as Expert Systems, Knowledge Base Systems, Logical Reasoning Algorithms, Linguistic Intelligence etc. Integrative Tests of Major Application as Neutral Language Processing, Speech Recognition, Text To Voice Converter, Multigame Logistic, Image Recognition, Facial Sensing. System that acts Rationally : System that acts Rationally Rational Behavior Doing the “Right Thing”, is defined as the maximum global achievement on the basis of Information available. Can include thinking in support of “Reverse Action” or “Reflex Actions”. Here Programming comes in role. This Programming Approach basically supports the logical Concern on behalf of available information and can be done in different languages like LISP, PROLOG, C/C++ etc. Overviews Introduction : Overviews Introduction Artificial Intelligence is to understand human intelligence better on the basis of “Tested Theories of Human Intelligence” and “Logical Programs” Emulates it. Diverse of disciplines contribute to get goal of creating Intelligent Entities: Computer Science (Research & Development/Implementation) Psychology (Reasoning Analysis) Philosophy (Rational Approach) Linguistics (Structure & Meaning of Language) Human Biology (Neurology) Overview Modules : Overview Modules Intelligent and Rational Agent. Searching Algorithms. Multi-Gamming Approach. Neutral Language Processing. Syntactical Approach of Lisp. Neural Networks. ROBOTICS and Future. Intelligent and Rational Agent : Intelligent and Rational Agent An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators, as Robotic agent:- cameras and infrared range finders for sensors. The agent function maps from percept histories to actions: [f: P* A] Searching Algorithms : Searching Algorithms Tree Simulated Exploration of state space by generating successors of already-explored states. E.g. Multi-Gamming Approach : Multi-Gamming Approach Optimal Decision through “MINIMAX”, is defined as choose move to position with highest “MINIMAX” value = best achievable payoff against best play Slide 14: MINIMAX Properties:- Complete? Yes (if tree is finite) Optimal? Yes (against an optimal opponent) Time complexity? O(bm) Space complexity? O(bm) (depth-first exploration) Slide 15: α-β Pruning Slide 19: Properties of α-β Pruning:- Pruning does not affect final result Good move ordering improves effectiveness of pruning With "perfect ordering," time complexity = O(bm/2) doubles depth of search. A simple example of the value of reasoning about which computations are relevant (a form of met reasoning) Neutral Language Processing : Neutral Language Processing An approach to give machines the ability to read and understand Human Languages. Some straight forward Application of Natural Language Processing Include information retrieval and Machine Level Translation. Syntactical Approach of Lisp : Syntactical Approach of Lisp LISP is used to Introduces Intelligence to Machines in form of Applications. LISP (List of Processing) is writing order inform of List. It consists of:- Atom e.g. 3,5,k … etc.; List e.g. (1 3 7), (33 38 43),….. Etc. Arithmetic Operations:- Addition :- (+ 3 3) means to say- 3+3 Subtraction :- (- 4 (+ 3 3)) means to say- ((3+3)-4) Multiplication :- (* 2 (- 4 (+ 3 3)) 3) means to say- ((3+3)-4) *2 *3 Division :- (/ 5 (-2 (+ 4 5))) means to say- (((4+5)-2)/5) Neural Networks : Neural Networks These are Two Hot Research Areas in Artificial Intelligence are: Neural networks: Building a model of the brain and "training" that model to recognize certain types of patterns. Genetic algorithms: “Evolving" solutions to complex problems (especially problems that are intractable using other methods). General brain architecture: Many (relatively) slow neurons, interconnected. Dendrites serve as input devices (receive electrical impulses from other neurons) Cell body "sums" inputs from the dendrites (possibly inhibiting or exciting) If sum exceeds some threshold, the neuron fires an output impulse along axon. Neural Cell Of Human Body : Neural Cell Of Human Body ROBOTICS And Future : ROBOTICS And Future Robotics is the science and technology of ROBOTS. Researches are going on these days to implement the complete “Theories of Intelligence” and to make them capable for tasks as Object Manipulation, Navigation, Mapping and Motion-Planning.