Syllabus
1. GENERAL SPECIFICATIONS
Course Name: ARTIFICIAL INTELLIGENCE
Course Code: 207008
Course Duration: 17 weeks
Dictation Form: Technical – experimental
Weekly hours: Theory: 3 hours - Lab: 2h
Nature: Vocational Training
Number of credits: Four (04)
Prerequisites: 205007 - Operations Research I
Academic semester: 2011 – II
Teachers: Vera Pomalaza Virginia Teachers: Ana Maria Huayna, Hugo Vega, Rolando Maguiña
2. SOMMELIER
Artificial Intelligence, concepts, paradigms and applications in industry and services. Knowledge representation. Representation as a search problem of the state space. Blind search methods and informed. Intelligent man-machine games. Expert systems, architecture, taxonomy and applications. Inference Engine. Engineering knowledge, concepts, evolution, CommonKADS Methodology. Quality and Validation of Expert Systems, Introduction to Machine Learning (Machine Learning) and heuristics.
3. GENERAL PURPOSE
Students will gain knowledge in the area of Artificial Intelligence in general and develop basic aspects of game development, intelligent and expert systems, and its application in intelligent problem solving in the fields of industry and services.
4. SPECIFIC OBJECTIVES
After finishing the course the student will be able to:
1. Understand what is Artificial Intelligence and complexity of their problems. 2. Represent and solve problems of human game - machine through search techniques in a state space. 3. Knowing the different blind search strategies and informed. 4. Design and develop game software smart man-machine interaction using artificial intelligence techniques. 5. Understanding what expert systems are and know when to use them. 6. Knowing which is the Knowledge Engineering and a method for developing knowledge-based systems 7. Evaluate the quality of expert systems solution. 8. Designing and developing expert systems based on different inference engines (methods chaining), considering quality criteria. 9. Understand the concepts of machine learning and heuristic, its importance and its applications in industry and services.
5. ANALYTICAL CONTENTS OF WEEKS:
Week | Temas | Trabajos Teoria | Trabajos Laboratorio |
1 | Classification of Course Presentation algorithmic problems. Classification of algorithmic problems, problems P and NP. References: [4] Chapter 1, [1] Annex A. | ||
2 | Fundamentals of Artificial Intelligence Artificial Intelligence Definition. Intelligent machine. References: [1] Chapter 1, [2] Chapter 1, [9] Chapter 1. | ||
3 | Representación de problemas de juego humano máquina como búsqueda en un espacio de estado
| ||
4 |
| ||
5 | Métodos de búsqueda para juegos humano-máquina
Referencias: [1] Capítulo 5, [2] Capítulos 6, [3] Capítulos 4, [4] Capítulos 6, [9] Capítulos 12. 2do control de lectura | ||
6 | Fundamentos de sistemas expertos
| ||
7 |
| ||
8 | Examen Parcial | Examen Parcial |
|
9 | Presentación de trabajos computacionales
| ||
10 | Adquisición de Conocimiento
Referencias: [6] Capítulos 6, [7] Capítulos 19. 3er control de lectura. |
| |
11 | Desarrollo de sistemas expertos basados en reglas
| ||
12 | Calidad y validación de sistemas expertos
Referencias: [4], [7] Capítulo 21. 4to control de lectura. |
| |
13 | Introducción a Machine Learning.
| ||
14 | Introducción a heurísticas y meta-heurísticas.
| ||
15 | Presentación de trabajos computacionales
| ||
16 | Examen Final | ||
17 | Examen final (solo para aquellos que no dieron examen parcial o final) |
5. METODOLOGÍA
El curso se desarrolla a través de actividades teórico - Prácticas, dando énfasis a aplicaciones en la industria y servicios. Los estudiantes, organizados en equipos de 3 desarrollarán dos trabajos computacionales. Durante las sesiones de teoría se discutirán la resolución de problemas propuestos. Durante las sesciones de laboratorio se evaluarán las lecturas así como el avance de los trabajos computacionales.
6. EVALUACIÓN
El promedio final (PF) se determina de la forma siguiente:
PF = 0.025(CL1+CL2+CL3+CL4) + 0.075(TB1+TB2) + 0.15*LA + 0.30*(EA+EB)
Donde:
CLx: Controles de Lecturas (CL1, CL2, CL3 y CL4)
TB1:Trabajo Grupal (Juegos Inteligentes Hombre - Máquina)
TB2: Trabajo Grupal (Sistemas expertos)
EA: Examen Parcial
EB: Examen Final
LA: Laboratorio
El alumno podrá sustituir la nota del examen parcial o final siempre que no haya podido dar alguno de estos exámenes. Solo serán evaluados los alumnos que presenten 70% o más de asistencias.