1 / 7

CS6700 Advanced AI Bart Selman

CS6700 Advanced AI Bart Selman. Admin. Project oriented course Projects --- research style or implementation style with experimental component. 1 or 2 students 70% grade Readings: Class presentation and discussion 20%

robbin
Download Presentation

CS6700 Advanced AI Bart Selman

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. CS6700 Advanced AIBart Selman

  2. Admin • Project oriented course • Projects --- research style or implementation • style with experimental component. • 1 or 2 students • 70% grade • Readings: Class presentation and discussion 20% • (group of 2 or 3 is assigned 1 or 2 papers) • Participation --- 10% • Weekly lecture on Wedn. at 3:35pm

  3. Projects Very open-ended Go for BIG ideas! (No such thing as “failure.”) E.g. Can you evolve a language from scratch? Can you learn from “reading”? (E.g. game play from text on discussion boards) Mechanical Turk --- Human-computing hybrids Mine info from twitter feeds Boost game play via “mimicry”

  4. Topics list • AI --- general intro • Knowledge-based approaches • --- inference • --- problem hardness • --- connections to statistical physics • Statistical and probabilistic inference • --- connections to graphical models / Bayes nets • --- Markov Logic • Multi-agent systems • --- combinatorial auctions • --- multi-agent reasoning • Planning • But, also, to get you thinking about future challenges / • directions for AI.

  5. In Class Discussion Papers Examples topics: AI: Science or Engineering? IBM’s Watson (world-level Jeopardy) Dr. Fill (world-level NYT crossword solver) Iamus (world-level classical music composition) Deep Learning (automatic structure discovery)

  6. Knowledge Intensive AI Knowledge-Data-Inference Triangle NLU Common Sense Computer Vision 20+ yr GAP! Google’s Knowl. Graph Iamus Watson Google Transl. Machine Learning Verification Dr. Fill Siri Robbin’s Conj. 4-color thm. Deep Blue Google Search (IR) Inference/Search Intensive Data Intensive Semantic Web

  7. Knowledge or Data? Last 5 yrs: New direction. Combine a few general principles / rules (i.e. knowledge) with training (ML) on a large expert data set to tune hundreds of model parameters. Obtain world-expert performance using inference. Examples: --- IBM’s Watson / Jeopardy --- Dr. Fill / NYT crosswords --- Iamus/ Classical music composition Performance: Top 50 or better in the world! Is this the key to human expert intelligence? Discussion / readings topic.

More Related