This course will introduce participants to machine learning, focusing more on the practical and applied aspects rather than theory. The course will discuss machine learning concepts, and briefly introduce Python, PyCharm environment, Scikit-learn, Numpy, Anaconda, and Keras toolkits.
Regression as a basic machine learning method will be discussed and practised. Different models and examples of regression will be reviewed. Support Vector Machines (SVM) along with their applications in function estimation and classification will also be introduced. We will also discuss artificial neural networks and introduce deep learning.
Participants will learn how to implement machine learning to solve real-life problems more productively and efficiently.
At the end of the course, participants will be able to:
- Understand the way regression, support vector machines (SVM), and artificial neural networks (ANN) work
- Recognise the applications, advantages and disadvantages of regression, SVM, and ANN methods
- Design and implement basic regression, SVM-based, and ANN-based algorithms in clustering, classification, and function estimation applications
- Getting familiar with the course
- A brief review of AI
- Machine Learnings definitions and terms
- Machine Learning applications
- Introduction to Python programming
- Linear regression
- Non-linear regression
- How to implement regression in Python?
- What are Support Vector Machines (SVM)?
- SVM implementation
1. Artificial Neural Networks
- What are Artificial Neural Networks (ANNs)?
- Basic ANN models: Perceptron
- Multilayer Perceptrons (MLP) and non-linear mapping
- Supervised and unsupervised schemes
- How to implement and train an MLP in Python?
- Evaluation and Performance Measurement
2. Deep Learning Introduction
- What is Deep Learning?
- Why Deep Learning is Important and Effective?
- State of the Art Instances
- Basic Deep Learning Models
- Deep Learning Environments
3. Assessment: Mini project
Python and Orange
Basic AI knowledge and basic Python programming skills
Who Should Attend
Data Analysts, IT Experts, Chief Technology Officers (CTOs), Technical Advisors, Intermediate-level Managers
Mode of Training
Dr. Amirhassan Monajemi
Amirhassan Monajemi is a Senior Lecturer in AI and Data Science with the School of Continuing and Lifelong Education (SCALE) at the National University of Singapore (NUS). Before joining the NUS, he was with the Faculty of Computer Engineering, University of Isfahan, Iran, where he was serving as a professor of AI, Machine Learning, and Data Science. He was born in 1968 in Isfahan, Iran. He studied towards BSc and MSc in Computer Engineering at Isfahan University of Technology (IUT), and Shiraz University respectively. He got his PhD in computer engineering, pattern recognition and image processing, from the University of Bristol, Bristol, England, in 2005. His research interests include AI, Machine Learning, Machine Vision, IoT, Data Science, and their applications.
He has taught the artificial intelligence courses, including AI, Advanced AI, Expert Systems, Decision Support Systems, Neural Networks, and Cognitive Science since 2005 at both undergraduate and postgraduate levels. He was awarded the best university teacher of the province in 2012. He also has studied Learning Management Systems, E-Learning, and E-Learning for workplaces since 2007.
Dr. Monajemi has registered a few patents in the fields of AI, Machine Vision, and Signal Processing applications, including an AI and machine vision-based driver drowsiness detection system and a low power consuming spherical robot. He also has published more than a hundred research papers in peer-reviewed, indexed journals and international conferences (IEEE, Elsevier, Springer, and so on), and supervised several Data Science, IoT, and AI industrial projects in various scales, including Isfahan intelligent traffic system delivery and testing, and red light runners detection. He is experienced in different sub-domains of Artificial Intelligence and Machine Learning, from theory to practice, including Deep Learning, Logic, and Optimization.