2022 - 2023

This course covers advanced and latest research issues on Natural Language Processing, including Sentiment Analysis, Topic Modeling, Text Clustering, Text Classification, Information Extraction, Dialogue System, Question Answering, Summarization, Text Generation, Knowledge Graph, and Machine Translation. The discussion of these advanced topics will include some of the latest pre-trained models such as BERT, Hugging Face, GPT, and ChatGPT.

This course covers advanced and latest research issues on Natural Language Processing, including Sentiment Analysis, Topic Modeling, Text Clustering, Text Classification, Information Extraction, Dialogue System, Question Answering, Summarization, Text Generation, Knowledge Graph, and Machine Translation. The discussion of these advanced topics will include some of the latest pre-trained models such as: BERT, Hugging Face, GPT, ChatGPT and etc.

Thesis work demonstrates the mastery of relevant knowledge and research skills of students. The degree of knowledge and skills acquired throughout the programme, including skills in programming, critical and analytical thinking, can be exhibited in a substantial research paper that meets academic standard. It can also enculturate interest in independent and lifelong learning.

This course demonstrates the mathematic foundations of deep learning, based on which, exhaustive deep learning principles are lectured, including feed-forward neural network, regularization, optimization, convolution neural network, and sequence modeling. This is followed by deep learning application of basic methods into computer vision and natural language processing. Besides, with teamwork and communication skills, the students are required to implement a framework of computational graphs such as Tensorflow and PyTorch.

from Office of Academic Affairs, Xiamen University Malaysia. The following is (are) the course(s) that you will teach in the Academic Session: 2023/04.

This course provides basic knowledge about machine learning problems and methods. Concepts include decision trees, neural networks, Bayesian Learning, Instance-Based Learning, Reinforcement Learning, and distributed learning. All the techniques are practiced within some existing tools, such as sklearn and Tensorflow. The students will work on a group project, presenting their application with the knowledge and skills from this course.

Lecturer: Dr Shamini Raja Kumaran (shamini.rajakumaran@xmu.edu.my)

Class Day and Time: 

Course Summary:

This course provides the basic knowledge of statistical learning, include discriminate analysis, factor analysis, Ridge Regression, AR, MA, ARMA, parametric sequence analysis and non-parametric sequence analysis.

Lecturer: Dr Shamini Raja Kumaran (shamini.rajakumaran@xmu.edu.my)

Day and Time:  Every Monday 9am - 110am (A4#102)(Week 1-15) (Lecture-Group 2)

Lab Classes : 

Every Wednesday 9am-10am(A1#111)(Week 1-15) (Group 3)

Every Wednesday 9am-10am(A1#111)(Week 1-15) (Group 4)

This course provides the basic knowledge of artificial intelligence and related mathematics. To be general and detailed, the topics include searching, heuristic searching, simulated annealing, gradient method, computational intelligence, decision trees, naïve bayes, k nearest neighborhood, linear models, support vector machine, deep learning components. Given the students are without math foundation, we provide the prerequisites in the first class, while in the final class, the students shall finish one project and present this project in class.

The course aims to enable students to acquire sufficient understanding and knowledge about sensors. The fundamentals of sensors, applications of modern sensors will be introduced in this course. 

This course covers some of the linguistic and algorithmic foundations of natural language processing. The aims of the course is to equip students for more advanced NLP techniques. The course is strongly empirical, using corpus data to illustrate both core linguistic concepts and algorithms, including language modeling, part of speech tagging, syntactic processing, the syntax-semantics interface, question answering, information extraction, semantic parsing, and aspects of semantic processing.

This course guides the students hand by hand for some introductory examples, such as template-based OCR, template-based Chatbot, Rule-based Expert System, Searching-based Five-in-Row, Seq2Seq Chatting mechanism, Logics-based Plan, Bayesian Analysis for inferring the user preference, Image Detection and Image Recognition.

This course demonstrates the mathematic foundations of deep learning, based on which, exhaustive deep learning principles are lectured, including feed-forward neural network, regularization, optimization, convolution neural network, and sequence modeling. This is followed by deep learning application of basic methods into computer vision and natural language processing.

Lecturer: Dr Shamini Raja Kumaran (shamini.rajakumaran@xmu.edu.my)

Class Day and Time: 

Thursday 1.00pm-3.00pm(A4#G10)(Week 1-15)

Friday 8.00am-9.00am(A1#102)(Week 1-15)

This course provides the basic knowledge of statistical learning, include discriminate analysis, factor analysis, Ridge Regression, AR, MA, ARMA, parametric sequence analysis and non-parametric sequence analysis.

This course provides the students with the foundational knowledge of computer vision and robots, such as early vision methods, mid-Level methods, high-level methods and end-to-end deep learning methods.

See you in the classroom!

Lecturer: Goh Sim Kuan (simkuan.goh@xmu.edu.my)