Presentation is loading. Please wait.

Presentation is loading. Please wait.

Introduction to AI & AI Principles (Semester 1) REVISION LECTURES (Term 3) John Barnden Professor of Artificial Intelligence School of Computer Science.

Similar presentations


Presentation on theme: "Introduction to AI & AI Principles (Semester 1) REVISION LECTURES (Term 3) John Barnden Professor of Artificial Intelligence School of Computer Science."— Presentation transcript:

1 Introduction to AI & AI Principles (Semester 1) REVISION LECTURES (Term 3) John Barnden Professor of Artificial Intelligence School of Computer Science University of Birmingham, UK

2 TODAY: Any questions for later? Nature of Exam Review of the term Dealing with Questions, if time TOMORROW: More questions if desired. Otherwise just an extra office hour

3 Questions for me to log?

4 Nature of the Examination

5 Format uOne and a half hours (for Intro to AI). (= Half of AI Principles exam.) uFour questions. Two have several parts. uSuggestion: 10-15 minutes for initial read-through and thinking, then up to about 15 minutes for answering each question, leaving about 15 minutes for final checking/refining. uNo explicit choice between questions or question parts, but one question allows considerable latitude as to what areas of AI you address. uSome question parts: broadly similar in style to some questions in formative Exercise Sets. uMixture of particular technical tasks and broad mini-essay-style tasks.

6 Material, 1 uMy own lecture material. uMaterial from all Guest Lectures. uOther Bullinaria slides: l Search l Production Systems (and my own notes on his slides on this topic) l Expert Systems uChapters (or chapter parts) in the Weekly Reading Assignments on module webpage. uAnswers to the formative Exercise Sets in Term 1.

7 Material, 2 uDon't be spooked by examinations before 06-07!! My coverage of material is new. uKnowledge of textbook chapters or chapter parts other than those I've listed ISN’T expected. uKnowledge of Bullinaria slides other than those I point to from my list of weekly lecture slides ISN’T expected. uKnowledge of fine technical details in guest lectures and book chapters ISN’T expected. (I’m only expecting the main concepts and overall grasp of main examples.) uBut of course knowledge of all the above types could be helpful and impressive.

8 REVIEW of the material

9 Review, 1 uNature of AI: aims, applications, branches, issues. Difference from CS in general. u“Intelligence” and its connection to “stupidity”. uExpert AI versus Everyday (“Common-Sense”) AI. uWhy everyday AI is difficult. l Language processing, vision, planning, common-sense reasoning, etc.

10 Review, 2 uWhy planning, common-sense reasoning, language processing, etc. may need representation. uWhy natural language is problematic for this … while also having many strengths, and is occasionally used (e.g., in widely-used ConceptNet from BT). uWhat we need to represent: entities (incl. situations, feelings, …), properties, relationships, groups, propositional structure, generalization/quantification, … uTypes of reasoning we need to do.

11 Review, 3 u Taster of logic. l Captures entities, properties, relations, extreme forms of quantification, basic forms of propositional structure. Can also handle groups of entities. l Aims of logic: clarity and simplicity compared to NL; systematic, sound reasoning; general applicability; common format for comparison. uIntro to semantic networks (and frames). uProduction systems (and expert systems).

12 Review: Guest Lectures uComputer games uRobotics uVision (2 lectures) uAI in HCI uLearning uNeural networks uEvolutionary computing uEvolution of language, nature of representation, etc. (Sloman)

13 Review: General Themes in AI uUncertain,vague, conflicting, missing, or diverse info. Huge amounts of info, of varying relevance. uHence: satisficing, graceful degradation, heuristic processing (i.e., using rules of thumb). uContext-sensitivity; incl. relativity to agents’ purposes. uTask variability, learning, adaptation, repair (e.g., of plans). uRepresentation. uReasoning. uSearch.

14 Questions from before or new ones


Download ppt "Introduction to AI & AI Principles (Semester 1) REVISION LECTURES (Term 3) John Barnden Professor of Artificial Intelligence School of Computer Science."

Similar presentations


Ads by Google