ai-lect15 - Course Overview and summary We have discussed....

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Course Overview and summary We have discussed… - What AI and intelligent agents are - How to develop AI systems  - How to solve problems using search - How to play games as an application/extension of search - How to build basic agents that reason logically, using propositional logic - How to write more powerful logic statements with first-order logic - How to properly engineer a knowledge base - How to reason logically using first-order logic inference - Examples of logical reasoning systems, such as theorem provers - How to plan - Expert systems - What challenges remain
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Acting Humanly: The Turing Test Alan Turing's  1950 article  Computing Machinery and  Intelligence  discussed conditions for considering a  machine to be intelligent “Can machines think?”  ←→  “Can machines behave intelligently?” The Turing test (The Imitation Game): Operational definition of  intelligence. Computer needs to posses:   Natural language processing,  Knowledge representation, Automated reasoning, and Machine  learning
Background image of page 2
3 What would a computer need to pass the Turing test? Natural language processing:  to communicate with examiner. Knowledge representation:  to store and retrieve information  provided before or during interrogation. Automated reasoning:  to use the stored information to answer  questions and to draw new conclusions. Machine learning:  to adapt to new circumstances and to detect and  extrapolate patterns. Vision  (for Total Turing test): to recognize the examiner’s actions  and various objects presented by the examiner. Motor control  (total test): to act upon objects as requested. Other senses  (total test): such as audition, smell, touch, etc.
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 What would a computer need to pass the Turing test? Natural language processing:  to communicate with examiner. Knowledge representation:  to store and retrieve information  provided before or during interrogation. Automated reasoning:  to use the stored information to answer  questions and to draw new conclusions. Machine learning:  to adapt to new circumstances and to detect and  extrapolate patterns. Vision  (for Total Turing test): to recognize the examiner’s actions  and various objects presented by the examiner. Motor control  (total test): to act upon objects as requested. Other senses  (total test): such as audition, smell, touch, etc. Core of the problem, Main focus of 561
Background image of page 4
5 What is an (Intelligent) Agent? Anything that can be 
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 135

ai-lect15 - Course Overview and summary We have discussed....

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online