CSE 571 14362 Artificial Intelligence TTh 3 15

CSE 571 (14362) Artificial Intelligence (TTh 3: 15 – 4: 30 PM, BYAC 150) Instructor: Chitta Baral Office hours: TTh 4: 40 to 5: 30 PM

Meaning of the word: ``intelligence'' • 1 (a) The capacity to acquire and apply knowledge. (b) The faculty of thought and reason. (c) Superior powers of mind. See Synonyms at mind. • 2 An intelligent, incorporeal being, especially an angel. • 3 Information; news. See Synonyms at news. • 4 (a) Secret information, especially about an actual or potential enemy. (b) An agency, staff, or office employed in gathering such information. (c) Espionage agents, organizations, and activities considered as a group • Source: The American Heritage® Dictionary of the English Language, Fourth Edition Copyright © 2000 by Houghton Mifflin Company. Published by Houghton Mifflin Company. All rights reserved.

Meaning of the word: ``intelligence'' • n • 1: • • • the ability to comprehend; to understand profit from experience [ant: stupidity] 2: a unit responsible for gathering and interpreting intelligence 3: secret information about an enemy (or potential enemy); "we sent out planes to gather intelligence on their radar coverage" 4: new information about specific and timely events; "they awaited news of the outcome" [syn: news, tidings, word] 5: the operation of gathering information about an enemy [syn: intelligence activity, intelligence operation] Source: Word. Net ® 1. 6, © 1997 Princeton University

Artificial Intelligence • Based on the above, `artificial intelligence' is about the science and engineering necessary to create artifacts that can – acquire knowledge, • learn from experience • learn from reading and processing natural language text – reason with knowledge (leading to doing tasks such as planning, explaining, diagnosing, acting rationally, etc. ),

Two main parts of this course • Knowledge representation, reasoning (and declarative problem solving) – 50% from the text book – 10% from the book `Causality' by Judea Pearl and papers by Judea Pearl and Joe Halpern; and on Bayes' nets • Learning – 10% on learning logical rules such as Progol, FOIL etc. – 10% on learning Bayes' nets, causal structures etc. – 20% on natural language processing, Human language technology.

Syllabus from the text book • Chapter 1 (Sections 1. 1 -1. 3). • Chapter 2 • Chapter 3 (Sections 3. 1, 3. 1. 1 -3. 1. 3, 3. 1. 5, 3. 2. 1, 3. 2. 4, 3. 4. 1) • Chapter 4 • Chapter 5 (Sections 5. 1 -5. 4, 5. 6) • Chapter 8 (Sections 8. 1 -8. 3) • Time line: – – • 4 classes 3 classes 6 classes -- Ch 1, Ch 8 (Smodels and DLV syntax) -- Ch 2 and 3 -- Ch 4 -- Ch 5, some of Ch 8 Several papers for the other parts (to be listed)

Grading • Two tests (No finals) 30% – Test dates (Test 1 – March 24 th; Test 2 -- May 3 rd) – Test 2 may be rolled over to the project (need instructor permission) • One project 40% (demo during May 3 -6) – – • • Develop a Question answering system on a particular domain Decide on domain by Feb 15 th. First Status report March 10 th Second Status report April 21 st. Homework & programming assignments 20% Class participation 10% – attendance will be taken in every class; – coming late after the attendance has been taken will result in being marked absent and will count negatively. • first class disruption -- arriving late or a similar activity - without prior permission will count -1% of the grade; the next one -2%; and so on. )

Modus Operandi – for not non-NLP part • Students will be assigned material to read. • They have to come prepared to the class where I will ask questions and clarify things. • This will happen during the first 60 -65 minutes of the class. In the last 10 -15 minutes of the class I will motivate the content to be discussed in the next class.