AIML402 Advanced Artificial Intelligence

Overview

Modern AI representation systems and problem-solving techniques with a particular emphasis on machine learning.

About this paper

Restriction

COSC 343

Notes

Students with limited programming experience should also take AIML 401

Contact

adviser.computing@otago.ac.nz

Teaching staff

Dr Lech Szymanski (Lecturer)

Paper Structure

In this paper we will focus on the hard problems to be solved in artificial intelligence (AI), concentrating on the issue of how to get information about the world and how to make use of it. We will consider techniques for machine learning and probabilistic reasoning. Almost every human ability results from learning from experience: we will look at how these learning processes can be modelled computationally.

Topics to be considered include:

• Search and optimisation algorithms (including genetic algorithms)
• Probabilistic reasoning methods (including Bayesian methods)
• Machine learning algorithms (with a focus on neural networks and deep learning)

Teaching Arrangements

2x 1h Lectures per week

1x 2h Lab sessions per week

3x 2h tutorial

Textbooks

Artificial Intelligence: A Modern Approach (Fourth Edition), by Stuart Russell and Peter Norvig, Pearson 2020.

Course outline

View the course outline for AIML 402

Graduate Attributes Emphasised

Interdisciplinary perspective, Scholarship, Communication, Ethics
View more information about Otago's graduate attributes.

Learning Outcomes

Students who successfully complete the paper will:

• Gain a practical understanding of a selection of core concepts in AI research: planning and search, probabilistic reasoning, machine learning, decision trees, neural networks, sequential decisions, and deep learning.
• Strengthen their understanding of each core concept through practical exercises and experience with implemented systems.

Overview

Modern AI representation systems and problem-solving techniques with a particular emphasis on machine learning.

About this paper

Restriction

COSC 343

Notes

Students with limited programming experience should also take AIML 401

Contact

adviser.computing@otago.ac.nz

Teaching staff

Lecturer: Dr Lech Szymanski

Paper Structure

In this paper, we will focus on the hard problems to be solved in artificial intelligence (AI), concentrating on the issue of how to get information about the world and how to make use of it. We will consider techniques for machine learning and probabilistic reasoning. Almost every human ability results from learning from experience: we will look at how these learning processes can be modelled computationally.

Topics to be considered include:

• Search and optimisation algorithms (including genetic algorithms)
• Probabilistic reasoning methods (including Bayesian methods)
• Machine learning algorithms (with a focus on neural networks and deep learning)

Teaching Arrangements

Two 1-hour lectures per week

One 2-hour lab session per week

Three 2-hour tutorial

Textbooks

Artificial Intelligence: A Modern Approach (Fourth Edition), by Stuart Russell and Peter Norvig, Pearson 2020.

Course outline

View the course outline for AIML 402.

Graduate Attributes Emphasised

Scholarship, Communication.
View more information about Otago's graduate attributes.

Learning Outcomes

Students who successfully complete the paper will:

• Gain a practical understanding of a selection of core concepts in AI research: planning and search, probabilistic reasoning, machine learning, decision trees, neural networks, sequential decisions and deep learning.
• Strengthen their understanding of each core concept through practical exercises and experience with implemented systems.