A comprehensive introduction to Artificial Intelligence covering both theory and practice — from search algorithms and knowledge representation to machine learning, neural networks, and natural language processing. Designed for professionals and graduates seeking to understand and apply AI in their careers.
Course Overview
The NCC Education Short Course in Artificial Intelligence provides a comprehensive introduction to AI, exploring both theoretical and practical aspects. It covers classical AI techniques as well as modern machine learning approaches, giving students a full picture of how AI systems work and how to apply them in real-world business and technology contexts. Tools used include Python (with NLTK), WEKA, Scikit-Learn, and SWI Prolog.
Entry Requirements
- No formal prerequisites required
- Suitable for individuals with no prior AI or programming experience
- Basic familiarity with computing concepts is beneficial
Course Topics
1
Introduction to AI
History, definitions, and real-world applications of Artificial Intelligence
2
Problem Solving Using Search
Uninformed and informed search strategies: BFS, DFS, A* algorithm
3
Knowledge Representation
Logic, ontologies, semantic networks, and frames
4
Uncertain Knowledge
Bayesian networks, probability theory, and reasoning under uncertainty
5
Fuzzy Logic
Fuzzy sets, membership functions, and fuzzy inference systems
6
Machine Learning
Supervised, unsupervised, and reinforcement learning fundamentals
7
Neural Networks
Perceptrons, backpropagation, and deep learning architecture
8
Decision Trees
ID3, C4.5, and CART decision tree algorithms
9
Genetic Algorithms
Evolutionary computation, selection, crossover, and mutation
10
Expert Systems
Rule-based systems, inference engines, and knowledge bases
11
Natural Language Processing
Tokenisation, parsing, sentiment analysis, and language models
12
Intelligent Agents
Agent architectures, environments, and multi-agent systems
Students who complete TNEDU's AI short course understand how AI systems work from the inside — giving them a decisive advantage when using AI tools in their career, as well as a strong foundation for further study in data science or machine learning.
Tools Used
Python (with NLTK for NLP), WEKA (machine learning workbench), Scikit-Learn (ML library), SWI Prolog (logic programming).
Career Outcomes
AI Architect
Machine Learning Engineer
Data Scientist
Business Intelligence Developer
Big Data Engineer
AI Product Specialist
