Artificial Intelligence - Course Presentation

ArtificialIntelligence

Artificial IntelligenceCourse Presentation


Summary

MotivationsCourse PlanResourcesExam Methods


Motivations

Artificial Intelligence:

Machines that think and act like humans do

Voight-Kampff test in blade-runner


Motivations

Artificial Intelligence:

Machines that solve complex problems

Google Self Driving car


Related areas

AI highly interdisciplinaryProbability and StatisticsRoboticsLogicsAlgorithmsGame TheoryPattern Recognition and Machine Learning


Practical applications: Overview

SurveillanceEnvironmental monitoringSearch and Rescue operationsEnergy managementService RobotsGames, entertainment and educationComputer VisionMedical DiagnosisHardware/Software Verification...


Service Robots/Entertainment: CooperativeForaging

Decide who is in the best position to execute a task


Surveillance and Monitoring: mobile sensorexploration

A group of sensors cooperatively plans for most informativepaths


Surveillance and Monitoring: precisioneagriculture

Analyse data from greenhouse sensor network to maximizecrop yield and minimize infection(Post-doc: Alberto Castellini, Project: EXPO-AGRI)


Surveillance and Monitoring: Multi-RobotPatrolling

Allocate visit locations to a group of robots


Security: Active Malware Analysis

Use Reinforcememnt Learning to analyse malwarebehaviors (PhD: Riccardo Sartea)


Ride-Sharing: coalition formation

Form groups of riders to minimize fuel consumption(Post-Doc: Filippo Bistaffa)


Environmental Survey: Water Monitoring

Intelligent drones to monitor water quality


Water Monitoring: High level control for thedrones

Human interaction with team oriented plans(PhD student: Masoume Raeissi)


Water Monitoring: Planning informative paths

Active learning to devise informative paths for classification(PhD student: Lorenzo Bottarelli)


Water Monitoring: perception for autonomousbehaviors

Use computer vision to detect relevant features andsituations (Researcher: Domenico Bloisi)


Course Plan I

Problem Solving: Search (about 4 Lessons)Uninformed search (Breadth first, Depth First, IterativeDeepening, etc.)Informed Search (A*, Heuristics, Local Search andOptimization)

Constraint Processing (CSP, COP) (about 4 lessons)Contraint Satisfaction Problems, Constraint Networkand Graphical modelsBasic techniques for CSP (Consistency enforcing,Backtracking, Local Search)Tree-Decomposition (Dynamic Programming)Constraint Optimisation Problems


Course Plan II

Multi-Agent Systems (about 2 lessons)Distributed COPsReaching agreement

Prova parziale (approx. end of April)Adversarial Search (1 lesson)Plan representation and monitoring (1 lesson)Logic and Agents (about 2 lessons)

Logical AgentsBackground on Logic (propositional, FOL)Inference (DPLL, Resolution)

Probabilistic Reasoning (about 5 lessons)background on ProbabilityBayesian NetworkInference (complete and approximate)Markov Decision Processes and ReinforcementLearning


Resources

Text BooksArtificial Intelligence: a modern approach 2nd EditonRussel and Norvig (English edition)Constraint Processing R. Dechter

Other MaterialScientific Papers, Slides, etc.Will be available on web site

Web Page linkhttp://profs.sci.univr.it/ farinelli/courses/ia/ia.html


Exam modalities

Single-test modeSingle written test at the exam day

Partial test mode: Two tests C1 + [C2 or P]C1 and C2: solve simple exercises/describe techniquesstudied during the courseP:

project to be developed at home (see below)

only to the exams right at the end of the class (SummerSession)partial written test C1: half-way through the course C2:at the end of the course.project (P) can be done in collaboration with anotherpersonFinal grade: 50%C + 50%[C1 or P]

http://profs.sci.univr.it/~farinelli/courses/ia/ia.html


Projects

ProjectInstructor will propose a set of projectsStudents can: choose among the set of proposedprojects or propose other projectsProjects proposed by students must be validated by theinstructorProjects usually involve a programming part (in thelanguage most appropriate for the project)Students must hand to the instructor a report of theproject and developed code.Have a look at past projects on the course web site

Artificial Intelligence - Course Presentation

Documents