Advanced Artificial Intelligence
- Sciences
- 900 level
- 291 pages
- 16 units
This course introduces students to advanced concepts in Artificial Intelligence. It explores AI foundations, programming languages, and basic AI issues, including attention, search, control, and knowledge representation. Students will learn about applying AI techniques in natural language processing, scene analysis, expert systems, and robot planning. The course includes lab exercises in AI languages and studies different classes of expert systems, equipping students with practical AI expertise.
About this course
- Difficulty
- Advanced
- Study hours
- 208 hours
- Maths
- Intermediate
- Content
- Theoretical, practical, case study, problem solving
- Practical work
- Yes
- Basic programming skills
- Data structures and algorithms
- Calculus
- Linear Algebra
- Assignments
- Tutor marked assessments
- Final examination
What you'll read
The real module and unit structure of CIT903, taken from the course material NOUN publishes.
One paragraph, so you can see how it reads
CIT903 · Unit One: What is Artificial Intelligence?
This course aims to give students an in-depth understanding of AI with a focus of its application on expert systems. It is hoped that the knowledge would enhance the AI expertise of students to enable them develop AI based applications.
What you should be able to do
- Explain AI principles
- Implement AI programs
- Apply AI techniques
- Understand expert systems
- Analyze scenes
- Plan robot movements
- Represent knowledge
What it prepares you for
- AI Engineer
- Data Scientist
- Robotics Engineer
- Software Developer
- AI Consultant
- Healthcare
- Finance
- Robotics
- Manufacturing
- Transportation
- Python
- LISP
- PROLOG
- OpenCV
- KEE
Where it gets hard
The units students slow down on, and what makes each one heavy.
- Module 2: BASIC AI ISSUES
Unit Three: Adversarial Search (Game Tree)
Adversarial search algorithms involve complex decision-making processes, requiring a deep understanding of game theory and search space exploration.
- Module 2: BASIC AI ISSUES
Unit Four: knowledge representation
Knowledge representation requires understanding of formal logics and the ability to translate informal knowledge into formal terms.
- Module 3: APPLICATION OF AI TECHNIQUES
Unit Two: Scene Analysis
Scene analysis involves complex mathematical concepts related to image formation and 3D reconstruction.
A suggested way through it
13 weeks, about 54 hours in total. Yours will differ.
- Week 1Module 1: INTRODUCTION
Unit 1: What is Artificial Intelligence? · 4 hours
Define AI, Turing Test, cognitive modeling, rational agent approach. Explain the foundations and advantages of each approach.
- Week 2Module 1: INTRODUCTION
Unit 2: The State of Art in AI · 4 hours
Discuss robotic vehicles, speech recognition, autonomous planning, game playing, logistics planning, robotics, machine translation.
- Week 3Module 1: INTRODUCTION
Unit 3: AI Programming Languages · 4 hours
Explore Python features, advantages, and libraries for AI. Understand Python's role in AI development.
- Week 4Module 1: INTRODUCTION
Unit 4: Types of AI · 4 hours
Understand Narrow AI, General AI, and Super AI. Explore Reactive Machines, Limited Memory, Theory of Mind, and Self-Awareness.
- Week 5Module 2: BASIC AI ISSUES
Unit 1: Attention · 4 hours
Understand attention in Narrow AI and AGI. Explore Artificial and Natural Attention Systems.
- Week 6Module 2: BASIC AI ISSUES
Unit 2: Search and Control · 5 hours
Define problem-solving agents and search terminologies. Differentiate uninformed and informed search algorithms.
- Week 7Module 2: BASIC AI ISSUES
Unit 2: Search and Control · 5 hours
Continue studying search and control algorithms. Apply search algorithms to solve problems.
- Week 8Module 2: BASIC AI ISSUES
Unit Three: Adversarial Search (Game Tree) · 4 hours
Explore game trees, minimax algorithm, and alpha-beta pruning. Understand adversarial search strategies.
- Week 9Module 2: BASIC AI ISSUES
Unit Four: knowledge representation · 4 hours
Understand knowledge representation concepts. Explore different knowledge representation approaches.
- Week 10Module 3: APPLICATION OF AI TECHNIQUES
Unit One: Natural Language · 4 hours
Explore language models, text classification, and information retrieval. Understand natural language processing techniques.
- Week 11Module 3: APPLICATION OF AI TECHNIQUES
Unit Two: Scene Analysis · 4 hours
Understand image formation and early image-processing operations. Explore object recognition and 3D world reconstruction.
- Week 12Module 3: APPLICATION OF AI TECHNIQUES
Unit Three: Expert Systems · 4 hours
Understand expert systems characteristics and components. Explore rule-based expert systems and knowledge engineering.
- Week 13Module 3: APPLICATION OF AI TECHNIQUES
Unit Four: Robot Planning · 4 hours
Explore robot planning concepts, configuration space, and motion planning. Understand uncertain movements and control techniques.
Preparing for the exam
- Review all tutor-marked assignments (TMAs) and self-assessment exercises, focusing on areas where you encountered difficulties.
- Create concept maps linking key topics from each module to reinforce understanding of interconnected concepts.
- Practice implementing basic AI algorithms (search, classification) in Python to solidify practical skills.
- Focus on understanding the differences between various AI techniques and their appropriate applications.
- Study the mathematical foundations of AI, including probability, statistics, and linear algebra, to tackle complex problems.
- Practice solving problems related to knowledge representation, inference, and reasoning to enhance problem-solving abilities.
- Create a study schedule that allocates sufficient time for each module, prioritizing challenging units.
- Form study groups to discuss and clarify complex concepts, share insights, and practice problem-solving together.
- Review the course guide and objectives to ensure comprehensive coverage of all topics.
- Focus on understanding the underlying principles and assumptions of each algorithm, not just memorizing formulas.
Questions students ask about this course
What is CIT903 about?
This course introduces students to advanced concepts in Artificial Intelligence. It explores AI foundations, programming languages, and basic AI issues, including attention, search, control, and knowledge representation. Students will learn about applying AI techniques in natural language processing, scene analysis, expert systems, and robot planning. The course includes lab exercises in AI languages and studies different classes of expert systems, equipping students with practical AI expertise.
How many units does CIT903 have?
CIT903, Advanced Artificial Intelligence, has 16 units across 4 modules, over 291 pages of course material. You can read it one unit at a time.
Is CIT903 hard?
CIT903 is rated advanced level, with intermediate mathematical content. It is mostly theoretical, practical, case study and problem solving work, and it has a practical component.
How long does CIT903 take to study?
About 208 hours of study, spread across its 16 units.
How is CIT903 assessed?
CIT903 is assessed by assignments, tutor marked assessments and final examination.
What do I need before starting CIT903?
Basic programming skills Data structures and algorithms Calculus Linear Algebra
What can I do with CIT903?
AI Engineer, Data Scientist, Robotics Engineer, Software Developer and AI Consultant.