|
|
|
6.034 ARTIFICIAL INTELLIGENCE
introduces representations, techniques, and architectures used to build
applied systems and to account for intelligence from a computational
point of view. Applications of rule chaining, heuristic search, logic,
constraint propagation, constrained search, and other problem-solving
paradigms. Applications of decision trees, neural nets, SVMs and other
learning paradigms.
PREREQUISITES
- 6.001
We will have regular assignments that expect you to be able to read and write Scheme. This is the only formal pre-requisite.
- 18.02
We will assume that you know what the chain rule is and what a dot
product is, and a partial derivative, etc. If you have not taken this,
you should really wait to take the subject until you have.
TOPICS
The course covers three major areas:
- Search (2 weeks)
- Graph search
- Constraint satisfaction
- Games
- Knowledge representation and Inference (5 weeks)
- Propositional and First Order Logic
- Rule-based systems
- Natural Language
- Machine learning (5 weeks)
- Nearest Neighbors
- Decision Trees
- Neural Networks
- SVM
Subject Objectives
A student completing 6.034 will be able to:
Objective
1) Explain the basic knowledge representation, problem solving, and learning methods of Artificial Intelligence
2) Assess the applicability, strengths, and weaknesses of the basic
knowledge representation, problem solving, and learning methods in
solving particular particular engineering problems
3) Develop intelligent systems by assembling solutions to concrete computational problems
4) Understand the role of knowledge representation, problem solving, and learning in intelligent-system engineering
5) Appreciate the role of problem solving, vision, and language in
understanding human intelligence from a computational perspective
And many 6.034 students will, as measured by exit survey:
6) Develop an interest in the field sufficient to take more advanced subjects
Desired Subject Outcomes
A student completing 6.034 will be able to:
|
|
|
|
|
|
|
# |
|
|
|
Outcome |
|
|
|
|
Related Objective |
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
|
|
|
Predict the behavior of forward-chaining and backward-chaining rule-based systems |
|
|
|
|
1, 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
|
|
Predict
the behavior and estimate the cost in time and space of various
heuristic and optimal search methods (depth-first, breadth-first,
best-first, uniform-cost, and A*), and choose the appropriate method
for particular problems |
|
|
|
|
1, 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
|
|
|
Predict
the behavior of various constraint-satisfaction methods (backtracking,
forward-checking, constraint propagation), and choose the appropriate
method for particular problems |
|
|
|
|
1, 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
|
|
|
Develop
small logic-based, rule-based and search-based systems, predict
performance characteristics, and describe the role of rule-chaining and
search in intelligent-system engineering |
|
|
|
|
3, 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
|
|
|
Use rules and logic to represent behavioral, classification, and causal knowledge |
|
|
|
|
1, 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
|
|
|
Apply basic machine learning methods such as nearest neighbors, identification trees, neural nets, and genetic algorithms |
|
|
|
|
1, 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
|
|
|
Predict the behavior of the basic machine-learning methods, and choose the appropriate method for particular problems |
|
|
|
|
1, 2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
|
|
Modify and extend simple implementations of the subject's representations and methods |
|
|
|
|
3, 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
|
|
|
Develop
small learning systems, predict performance characteristics, and
describe the role of learning in intelligent-system engineering |
|
|
|
|
3, 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
|
|
Discuss key issues in knowledge representation, problem solving, and learning |
|
|
|
|
1, 2, 3, 4, 5, 6 |
|
|
|
|
|
|
|
COURSE ORGANIZATION
2 x 1.5 hr classes (Two sessions/week, 1.5 hour/session)
1 recitation with TA (One session/week)
- On-line text + exercises
- Recommended books (available at Quantum & Amazon)
- Nilsson, AI: A New Synthesis, or
- Russell & Norvig, AI: A Modern Approach (2nd ed)
- On-line problem set
- 2 in-class quizzes
- Final
GRADING
- 30% Final
- 40% Quizzes
- 15% On-line assignments
- 15% Recitation Participation
- The on-line exercises and problems are an essential component of
the subject and are required. A 90% score on the on-line assignments
gets full credit. There is no difference between 90% and 100%. Scores
below 75% will lead to a grade of Incomplete in the subject.
- Problems submitted late will receive half credit unless you have a valid reason and make an arrangement with your TA.
COLLABORATION
- Everything you do for credit in this subject is supposed to be your own work; this includes on-line work.
- You can talk to other students (and TAs) about approaches to
problems, but then you should sit down and do the problem yourself.
This is not only the ethical way but also the only effective way of
learning the material.
|
|
|
|