Knowledge-Based AI: Cognitive Systems
Georgia Institute of Technology via Udacity
-
438
-
- Write review
Overview
This class is offered as CS7637 at Georgia Tech where it is a part of the Online Masters Degree (OMS). Taking this course here will not earn credit towards the OMS degree.
This is a core course in artificial intelligence. It is designed to be a challenging course, involving significant independent work, readings, assignments, and projects. It covers structured knowledge representations, as well as knowledge-based methods of problem solving, planning, decision-making, and learning.
The class is organized around three primary learning goals. First, this class teaches the concepts, methods, and prominent issues in knowledge-based artificial intelligence. Second, it teaches the specific skills and abilities needed to apply those concepts to the design of knowledge-based AI agents. Third, it teaches the relationship between knowledge-based artificial intelligence and the study of human cognition.
Why Take This Course?
At the conclusion of this class, you will be able to accomplish three primary tasks. First, you will be able to design and implement a knowledge-based artificial intelligence agent that can address a complex task using the methods discussed in the course. Second, you will be able to use this agent to reflect on the process of human cognition. Third, you will be able to use both these practices to address practical problems in multiple domains.
Syllabus
Unit 1: Introduction to KBAI and Cognitive Systems.
- Where Knowledge-Based AI fits into AI as a whole
- Cognitive systems: what are they?
- AI and cognition: how are they connected?
Unit 2: Fundamentals
- Semantic Networks
- Generate & Test
- Means-Ends Analysis
- Problem Reduction
- Production Systems
Unit 3: Common Sense Reasoning
- Frames
- Understanding
- Common Sense Reasoning
- Scripts
Unit 4: Planning
- Logic
- Planning
Unit 5: Learning
- Learning by Recording Cases
- Incremental Concept Learning
- Classification
- Version Spaces & Discrimination Trees
Unit 6: Analogical Reasoning
- Case-Based Reasoning
- Explanation-Based Learning
- Analogical Reasoning
Unit 7: Visuospatial Reasoning
- Constraint Propagation
- Visuospatial Reasoning
Unit 8: Design & Creativity
- Configuration
- Diagnosis
- Design
- Creativity
Unit 9: Metacognition
- Learning by Correcting Mistakes
- Meta-Reasoning
- AI Ethics
Taught by
Ashok Goel
Tags
Related Courses
-
Implementation Strategies: AI and Cognitive Computing
The University of British Columbia
-
AI Accountability Essential Training
-
AI: Constraint Satisfaction
Indian Institute of Technology Madras, NPTEL
-
AI for Business Leaders
BMW
-
Artificial Intelligence (AI)
Columbia University
4.1 -
Sample-based Learning Methods
University of Alberta, Alberta Machine Intelligence Institute
4.6
Reviews
3.0 rating, based on 2 reviews
-
Adam Tetelman is taking this course right now, spending 4 hours a week on it and found the course difficulty to be medium.
This course covers an interesting range in material in a structured way that is easy to follow.
Unlike many of the other more "hip" AI MOOCs out there, the lectures for this one are rather dry and difficult to follow. It feels a lot more like a traditional "classroom" experience than some other MOOCs I have taken lately.
Even given the boring lectures, there is a large amount of content and a heavy use of graphics to demonstrate key points.
-
Anonymous completed this course.
Too hypothetical. Could use practical programming exercises, like python notebook style that Andrew Ng does in his Coursera courses. The examples sometimes are a bit far of from being applicable. Otherwise it is very interesting and would do well with a deepening follow up course.