SC3000 Artificial Intelligence
Course Summary
This course aims to teach about intelligent agents and decision making processes in computers. It is an abstract course about Artificial Intelligence in general rather than deep diving into various models, which is covered in Neural Networks and Deep Learning. The topics you will cover are:
- Intelligent Agents
- Search Algorithms
- Markov Decision Process
- Reinforcement Learning
- Game Theory
- Neural Networks Basics
- Fuzzy Logic
- Fuzzy Inference Systems
Workload
The workload for this course is pretty standard with 2 hours for lectures and 1 hour for tutorials with additional labs in between. Most of the content is pretty digestable and thus the tutorials are pretty straightforward to do with a bit of thinking.
Projects
There are 2 projects, one group and the other individual. The group project is typically a search algorithm design based on the content covered on a dataset given by the professor. This project will take some time as each part of the project builds on the previous and requires knowledge taught in lectures. There is also a report submission at the end.
The second project is a simple neural network building exercise in Pytorch and it is very guided so do not worry as the prof provides plenty of examples.
Things to take note of
Unlike what many people expect, this is not a course designed to teach you about all the various AI systems that exist. Rather, it is a more general topic on what AI can and cannot do as well as some of the motivations behind having AI. The content can be a bit dry at times and difficult to understand but it is still doable at the end of the day.