1 / 11

AI Application Areas

AI Application Areas. Neural Networks and Genetic Algorithms These model the structure of neurons in the brain Humans are good at interpreting noisy input. Neural networks can also handle noisy data because they use a large number of fine-grained units

luz
Download Presentation

AI Application Areas

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. AI Application Areas • Neural Networks and Genetic Algorithms • These model the structure of neurons in the brain • Humans are good at interpreting noisy input. Neural networks can also handle noisy data because they use a large number of fine-grained units • Genetic algorithms contain genetic operator such as crossover and mutation CS360 AI & Robotics

  2. Physical Symbol System Hypothesis • Intelligence is achieved through: • Symbols to represent the problem domain • Operations on these symbols to generate solutions • Searching to select the most likely solution from this list • These can be narrowed down to: • Knowledge representation • Search CS360 AI & Robotics

  3. Knowledge Representation • Capture the essential features of a problem domain • Provide the information to a problem-solving procedure • Abstraction is important • Expressiveness vs. efficiency • The language should also be readable to humans CS360 AI & Robotics

  4. What Representation • It is important to select the most appropriate representation language for the problem CS360 AI & Robotics

  5. Representation Schemes • These should: • Express all the necessary information • Resulting code should be executed efficiently • Be a natural scheme for describing the knowledge • AI problems tend to be qualitative not quantitative and use reasoning not calculation CS360 AI & Robotics

  6. Handle Qualitative Knowledge CS360 AI & Robotics

  7. Searching CS360 AI & Robotics

  8. Exhaustive Search • Not possible for most problems • Chess contains different board states • Humans do not perform exhaustive searches • Humans make decisions based on judgment rules • These are called heuristics CS360 AI & Robotics

  9. Heuristic • A strategy for selectively searching a problem space • Heuristics are not foolproof • But it should come close to a solution • State space search formalizes the problem-solving process • Heuristics infuse the formalism with intelligence CS360 AI & Robotics

  10. Propositional Logic • Symbols of propositional logic (calculus) • Propositional symbols: • P, Q, R, S, … • Truth symbols: • True, false • Connectives: CS360 AI & Robotics

  11. Sentences • Every propositional symbol and truth symbol is a sentence • The negation of a sentence is a sentence • The conjunction of a sentence is a sentence • The disjunction of a sentence is a sentence • The implication of one sentence from another is a sentence • The equivalence of two sentences is a sentence CS360 AI & Robotics

More Related