Course Overview
Semiconductor manufacturing poses intricate challenges stemming from its complex processes, machinery, and parameters.
Manufacturing companies often struggle with the early detection of anomalies and optimising process parameters due to the high costs associated with traditional methods like Design of Experiment (DOE). Additionally, inadequate machine maintenance can lead to quality issues and financial losses, exacerbated by existing maintenance routines that may not effectively prevent breakdowns. To address these challenges, the semiconductor manufacturing sector requires Artificial Intelligence (AI) driven solutions.
This course is designed to empower industry professionals with advanced data analytics methodologies in AI and Machine Learning (ML). Through a combination of theoretical exploration, relevant case studies, and hands-on Python programming sessions, learners will develop a deep understanding of AI technologies and their application in semiconductor manufacturing.
By delving into real semiconductor data examples and utilising sample code, learners will gain practical experience in AI data analytics, enabling them to identify and address areas for improvement within their industries. Whether it's enhancing defect detection, optimising process parameters, or implementing predictive maintenance systems, this course equips learners with the tools and knowledge needed to drive meaningful change.
Who Should Attend
Professionals in the semiconductor manufacturing industry, including:
- Engineers
- Process, maintenance, and project managers
- Equipment designers and builders
- Professionals involved in the manufacturing process, quality control, and equipment maintenance
Prerequisites
-
Learners must have basic Python programming skills and statistical knowledge
What You Will Learn
Understanding, processing, and cleaning the data
- Performing data cleaning and manipulation
- Understanding data using plotting tools
Compressing and selecting the data dimensions
- Analysing the correlation and identifying the major factors
- Compressing and reducing the data dimensions
Building and evaluating supervised learning models
- Using the classification models method
Building and evaluating unsupervised learning models
- Using the clustering models method
Building and evaluating neutral network models
- Using neutral network models
Applying machine learning to the applications
- Understanding machine learning and its application
- Applying the methods learned to the application and evaluating the model's performance
Teaching Team
Zhou Junhong
Associate Professor, Engineering, Singapore Institute of Technology
Tan Rui Zhen
Associate Professor, Engineering, Singapore Institute of Technology
Wang Yu
Senior Professional Officer, Singapore Institute of Technology
Schedule
Course Run | Dates | Time |
---|---|---|
February – May 2025 Run |
7, 14, 21 & 28 Feb 7, 14, 21 & 28 Mar 4, 11, 18, 25 Apr 2 May |
1:00 pm – 5:00 pm |
Certificate and Assessment
A Certificate of Participation will be issued to participants who:
- Attend at least 75% of the course
- Undertake and pass non-credit bearing assessment during the course
Fee Structure
The full fee for this course is S$7,793.50.
Category | After SF Funding |
---|---|
Singapore Citizen (Below 40) | S$2,338.05 |
Singapore Citizen (40 & Above) | S$908.05 |
Singapore PR / LTVP+ Holder | S$2,338.05 |
Non-Singapore Citizen | S$7,793.50 (No Funding) |
Note: All fees above include GST. GST applies to individuals and Singapore-registered companies.
Course Runs
Frequently Asked Questions
-
Do I need to have coding skills for this course?
Basic Python programming skills are necessary, and you must install the Jupyter notebook software on your laptop.
New Engineering Micro-credentials Launching Soon!
Exciting news! We are introducing new micro-credentials in Electrical and Electronic Engineering & Infrastructure and Systems Engineering. Be among the first to know by registering your interest today! Register now →