Resources

Course requirements:

Three homeworks, obligatory, min.40%, 3x15 points

Midterm test, obligatory, min.40%, 0-60 points

Optional minor homeworks in 13 topics, 13 points

Overall (118points)

–44<: satisfactory (minimums from midterm and grand homeworks)
–55<: fair
–75<: good
–90<: excellent

Schedule

Wednesday, 8.30-10.00,, IE.224 (building I, wing E, 2nd floor)

Friday, 8.30-10.00, IE.224 (building I, wing E, 2nd floor)

Contact hour: Monday, 9.00-10.00, IE.423 (building I, wing E, 2nd floor)

Book:

S. Russell and P. Norvig Artificial Intelligence: A Modern Approach Prentice Hall, 2003, Second Edition

Homework guide: here (deadline for submission: 11th of December), see your consultant/contact: here

Updated BayesCube manual: here

BayesCube for XP/Win7/Win8, LINUX and Macintosh is available, please regularly check for the latest versions (and manual): here.

A special overview to support the solution of the homework.

Attached files: 
application/pdf iconL1: Introduction
application/pdf iconA.M.Turing: Computing machinery and intelligence
application/pdf iconOn our best behaviour (why my computer cannot understand me)
application/pdf iconL2a: AI approaches
application/pdf iconL2b: Agent architectures
application/pdf iconBoden: Computer models of creativity
application/pdf iconD.R.King: Automation of science
application/pdf iconL3: Uninformed search
application/pdf iconNewel&Simon: Computer science as empirical inquiry: symbols and search
application/pdf iconL4: Informed search (pdf) L5: Optimization
application/pdf iconMachine Discovery of Effective Admissible Heuristics
application/zip iconDemonstration of search strategies
application/pdf iconL6: Search Exercises
application/pdf iconL7: Constraint satisfaction problems
application/pdf iconA history of computer chess – from the Mechanical Turk to Deep Blue
application/pdf iconA short history of Computer Chess
application/pdf iconIs chess the drosophila artificial intelligence?
application/pdf iconL8: Game playing (from brute-frorce search and knowledge to levels of expertise)
application/pdf iconA.Tarski: Truth and proof
application/vnd.openxmlformats-officedocument.presentationml.presentation iconTransformational grammars
application/pdf iconL9: Propositional logic, truth and proof
application/pdf iconL10: Automated reasoning (intro in propositional logic)
application/pdf iconL11: First-order logic
application/zip iconProver9 demos
application/pdf iconpre L12: Logic: exercises (pre)
application/zip iconEarlier midterm exams
application/pdf iconMidterm results
application/pdf iconL13: Uncertainty
application/pdf iconBayes Offers a `New’ Way to Make Sense of Numbers
application/pdf iconBayes’ Theorem in the 21st Century
application/pdf iconBayesian networks without tears
application/pdf iconL14: Simple probabilistic models
application/pdf iconWhere Do the Numbers Come From
application/pdf iconL15: Bayesian networks
application/xml iconA spam model (in updated format)
application/xml iconThe alarm model (in updated format)
application/pdf iconL14: Homework - knowledge engineering
application/pdf iconBayesCube manual
application/pdf iconHomework guide
application/pdf iconHomework example with explanations
application/pdf iconConsultants
application/pdf iconL15: Exact inference in General BNs, in NBNs and in HMMs
application/pdf iconApplications and extensions of HMMs
application/pdf iconL16-1: Stochastic inference in BNs (only first part), utilizing parallel hw
application/pdf iconL16-2: Causal Bayesian networks (how to infer about effects of interventions)
application/pdf iconL16-3: Rational decisions, decision theory (how to quantify consequences)
application/pdf icon++Causal Bayesian networks (a little bit longer version)
application/pdf iconL17: Inductive, transductive inferences
application/pdf iconL18: From machine learning to data science
application/pdf iconAI topics
application/pdf iconexam 2014
application/pdf iconexam 2015jan ;-)
Submitted by Antal Péter on 2012. September 16. 19:42 | Last updated: 2017. September 4. 11:13
© 2010-2024 BME MIT