CET

Executive Certificate in Data Mining and Machine Learning

Overview

The Executive Certificate Programme in Data Mining and Machine Learning has been designed to support the strategic upskilling needs of employees in data Mining and machine learning as the Singapore government continues to advocate for wider adoption of analytics by businesses and industries to improve their productivity.

Requirements for Award of Executive Certificate

The award of the Executive Certificate in Data Analytics and Data Visualisation requires the successful completion within the maximum candidature of all four one modular-credit (1 MC) courses in the programme with at least a “C” grade in each course.

Participants who do not obtain at least a “C” grade in any course may repeat that course (with fees) to obtain a “C” grade, or better, as long as they have not exceeded the maximum candidature period.

Participants who do not obtain at least a “C” grade in any course within the maximum candidature will be issued a Certificate of Participation for that course.

Admission Criteria

Applicants seeking admission to the Executive Certificate Programme must have a Bachelor’s degree. Applicants may be required to show relevant work experience. Applicants with other qualifications and experience may be considered on a case by case basis, subject to approval by the Department of Statistics and Applied Probability.

Maximum Candidature

The maximum period of candidature for the Executive Certificate Programme is 24 months.

 

 

Programme Structure and Mode of Teaching, Learning and Delivery

The Executive Certificate Programme is offered on a part-time basis. International participants pursuing the programme will not be issued with student passes.

Each course in the programme will be delivered over three weeks using a combination of e-learning and facilitated learning. There will be assessments that track the progress and competency of the participants. Each course culminates in a data-analytic project which allows participants to showcase the knowledge they gained.

The courses for the Executive Certificate Programme are shown below:

Short Courses

MC

Contact Hours

Course Date

1.

DSA5831 Learning from Data: Principles and Practice

1

9 hours

12 October to 30 October 2020 (3 weeks)

2.

DSA5841 Learning from Data: Decision Trees

1

9 hours

10 November to 30 November 2020 (3 weeks)

3.

DSA5842 Learning from Data: Support Vector Machines

1

9 hours

19 November to 9 December 2020 (3 weeks)

4.

DSA5843 Learning from Data: Neural Networks

1

9 hours

2 November to 20 November 2020 (3 weeks)

DSA5831 Learning from Data: Principles and Practice

A variety of computer-based modelling and prediction tools are available to practitioners for learning from data collected in diverse fields including business, medicine and public policy to generate insights for decision-making. This course introduces participants to the trade-off between prediction and interpretability, the difference between regression and classification, and the basic principles of supervised and unsupervised learning. Participants will gain practical experience in the application of model selection and resampling methods to commonly used supervised regression and classification tools with real-world data.

DSA5841 Learning from Data: Decision Trees

Decision trees are supervised learning methods widely used for classification and regression. They are popular with practitioners because of the interpretability of the tree structures, reasonably good prediction accuracy, fast computational speed, and wide availability of software. In this course, participants will learn how to build and implement decision tree models, and assess their performance. The versatility of decision trees is demonstrated through practical applications. Participants will also learn how to improve prediction accuracy using bagging, random forests and boosting.

DSA5842 Learning from Data: Support Vector Machines

Support vector machines (SVMs) are a set of supervised learning methods widely used for classification. An SVM discriminates between two classes by generating a decision boundary that optimally separates classes after transforming the input data into a high-dimensional space. SVMs are popular because they are memory efficient and can address a large number of predictor variables. In this course, participants will learn how to build and implement SVMs, and assess their performance. The versatility of SVMs is demonstrated through practical applications.

DSA5843 Learning from Data: Neural Networks

Neural networks consist of input and output layers, as well as (in most cases) hidden layers consisting of interconnected units that transform the input data into an output. Their architecture makes them capable of learning and modelling nonlinear and complex relationships. In this course, participants will learn how to build and implement neural network models, and assess their performance. The versatility of neural networks is demonstrated through applications. Practical considerations about network architecture, model training and computational resources will be discussed.

 

Assessment and Grades

The short courses in the Executive Certificate Programme are graded.

Application and Course Fees

Application

Candidates interested in the Executive Certificate must apply for the Certificate at the NUS Online Application Portal: click on the last blue bar ‘For Alumni under the NUS Resilience & Growth Initiative 2020’ (this bar will only be available on 1 June), and then click on  ‘Executive Certificate Programmes’ under the application period of 10 August 2020 to 18 August 2020.

The next run of the Executive Certificate Programmes will commence in January 2021. Application is expected to open in November/December 2020. Please visit our webpage for the latest update.

 

Course Fees

Please visit NUS Resilience and Growth 2020 page https://scale.nus.edu.sg/nus-resilience-growth-2020 for the redemption of Virtual Voucher.

The University reserves the right to review and adjust the course fees and make changes to the programme structure and requirements as necessary and accordingly without prior notice.