Feb/Aug
Saturdays 9.00 am to 1.00 pm
Knowledge in Python, Coding
1.0 Python recap
1.1 procedural and OOP
2.0 Introduction to Machine Learning (Pasan)
2.1 Ideas of regression, classification, clustering, Neural Networks and Deep NN
3.0/4.0 Regression
linear and logistic
Discussion on SK learn and Keras for ML Including model training and evaluation
5.0/6.0 Classification
KNN, DT, SVM, Ensemble Systems
7.0 Clustering
5.1 K-means
8.0 Neural Networks
9.0 Machine Learning in the Cloud (MLaaS)
10.1ML OPS
10.2 Research Opportunities
1. Understanding and ability to apply the fundamental programming elements on Python and
its OOP concepts.
2. Understanding the types of machine learning algorithms in high level.
3. In-depth understanding of concepts and ability to apply supervised and unsupervised
machine learning techniques including Regression, Classification and Clustering for real-life
problems.
4. In-depth understanding of concepts and ability to apply Neural Network related machine
learning techniques like CNN, RNN and LSTM for real-life problems.
5. Ability to design, develop and deploy machine learning workflows in cloud based
environments like AWS, Azure, GCP.
6. Understanding of scientific research opportunities in the area of machine learning.
Those interested in learning ML and working in research and development in data-driven firms, as well as Research Students