Course webiste for BT5153
This course provides a comprehensive overview of advanced machine learning techniques, focusing on practical applications in business analytics. Emphasizing intuitive understanding, it covers trending machine learning models, particularly in Natural Language Processing (NLP). Students will engage in hands-on learning, exploring feature engineering, model selection, training, and the development of end-to-end machine learning projects. For sure, the curriculum includes a special segment on Large Language Models (LLMs). Python will be the primary programming language used for instruction and project implementation. The course aims to equip students with both theoretical knowledge and practical skills for real-world challenges.
To build a strong understanding of NLP and deep learning, I recommend the following books, blogs & papers.
In addition to books, there are excellent blogs that can deepen your understanding:
If you are not proficient in python, you may find some tutorials helpful.
During some lectures, you will be asked to check in. It might be in-class quiz or other forms of assignments.
There are two assignments and a mini Kaggle competition. Students are expected to complete these individual tasks to gauge their understanding of the course materials so as to prepare them for their Group Project and future data science tasks. Details of the individual assignments will be updated later.
You are required to form a project group with 4-5 members. Students can form their own teams and please fill out the google sheets. If a student can’t find a partner, we will team you up randomly (send the email to our TAs). Your project task is to apply the data mining and machine learning techniques that you have acquired to gain insights and draw interesting conclusions to a (business) problem. You are to apply (advanced) data mining and analytics tools (preferably in Python as Python tools are used as supplementary aids during the delivery of this course) to process structured and unstructured data available on the Web. You will then summarize your insights and present your conclusions using suitable visual aids. More detailed information can be found here.
Class Venue: COM1-0204
Date | Topic | Content | Assignment |
---|---|---|---|
Fri 01/17 | Introduction to Machine Learning and its Production | Link | N.A. |
Fri 01/24 | From BoW to Word2Vec | Link | Huggingface Tutorial |
Fri 01/31 | From Word2Vec to Transformers | Link | Form your team & Assignment I Out |
Fri 02/07 | LLM and its Practices I | Link | LangChain Tutorial & Assignment I Due |
Fri 02/14 | LLM and its Practices II | Link | N.A. |
Fri 02/21 | LLM and its Practices III | Link | Build your First RAG & Assignment II Out |
Sun 03/02 | Recess Week | N.A. | Proposal Due |
Fri 03/07 | Data Preparation | Link | Assignment II Due |
Fri 03/14 | ML Model Modelling | Link | Kaggle Starts |
Fri 03/21 | ML Model Evaluation | Link | N.A. |
Fri 03/28 | NO CLASS (NUS Well-Being Day) | N.A. | N.A. |
Fri 04/04 | ML Model Deployment | Link | Kaggle Competition |
Fri 04/11 | Why do ML Projects Fail in Business | Link | N.A. |
Fri 04/18 | No CLASS (Good Friday) | N.A. | Kaggle Report |
Sun 04/27 | N.A. | N.A. | Presentation and Final Report Due |