Download to read offline
Artificial Intelligence for Data Science.pptx
- 1. Artificial Intelligence Dr MKriushanth Assistant Professor Department of Data Science St. Joseph’s College (Autonomous) Tiruchirappalli
- 2. AI Problem • GamePlaying, Theorem Proving, Mathematical Problem Solving (Geometry) • No computer is fast enough to overcome the combinatorial explosion generated by most problems • AI focused on the sort of problem solving that we do every day
- 3. • Common-sense reasoning •General Problem Solver (GPS) • AI research progressed and techniques for handling perception, natural language understanding, Medical diagnosis and Chemical analysis.
- 4. Mundane Task • Perception •Vision • Speech • Natural Language • Understanding • Generation • Translation • Common-sense Reasoning • Robot Control
- 5. Formal Task • Games •Chess • Backgammon • Checkers-Go • Mathematics • Geometry • Logic • Integral calculus • Proving properties of programs
- 6. Expert Task • Engineering •Design • Fault finding • Manufacturing planning • Scientific analysis • Medical diagnosis • Financial analysis
- 7. The Underlying Assumption •Physical Symbol System Hypothesis
- 8. What is anAI Technique? • AI research is that intelligence requires knowledge. • It is Voluminous • Hard to characterize accurately • Constantly changing • It differs from data by being organized in a way that corresponds to the way it will be used
- 9. • Tic-Tac-Toe • Vectorelements 0 to 9 • 2 for Empty and 3 for X and 5 for O • Change of board position 8 3 9 1 5 9 6 7 2
- 10. Question answering • Programsthat read in English and then answer questions • Russia massed troops on the Czech border.
- 13. The level ofthe model • What is our goal in trying to produce programs that do the intelligent things that people do? • Are we trying to produce programs that do the tasks the same way people do?
- 14. • Two classes- • Programs in the first class attempt to solve problems that do not really fit our definition of an AI task. • They are problems that a computer could easily solve, although that easy solution would exploit mechanisms that do not seem to be available to people. • Elementary Perceiver and Memorizer (EPAM) • News papers fed in to the system and asked the question to answer • Cognitive science
- 15. Criteria for Success •Turing Test • Human performance • Machine has intelligence or think • The criteria for success for that particular program functioning in its restricted domain.
- 16. Production System • Setof rules that consists of a left side that determines the applicability of the rule and a right side that describes the operation to be performed if the rule is applied. • Knowledge / databases that contain whatever information is appropriate • A control strategy • A rule applier
- 17. • Control Strategy– BFS, DFS and Travelling sales man (Branch and Bound) • Heuristic search (Nearest neighbour) A heuristic is a technique that improves the efficiency of a search process, possibly by sacrificing claims of completeness. Heuristic are like tour guides. They are good to the extent that they point in generally interesting directions; they are bad to the extent that they may miss points of interest to particular individuals. Some process without sacrificing any claims to completeness.
- 18. Problem Characteristics • Isthe problem decomposable? • Can solution steps be ignored or undone? (8 Puzzle problem) • Is the universe predictable? • Is a good solution absolute or relative? (Travel sales man) • is the solution a state or path? • What is the role of knowledge? • Does the task require interaction with a person? • Problem classification