Department of CSE, BUET

Home
------------------------------------------------------------

Batch 30 Ongoing

Class Routine

IAC Facility Booking
------------------------------------------------------------
About Us
------------------------------------------------------------
Contact
------------------------------------------------------------
Login

Course Detail:

Course Name: Applied Machine Learning

Introduction

The Applied Machine Learning course at the Bangladesh-Korea Information Access Center (BK-IAC) is designed for professionals aiming to delve into the practical applications of machine learning. It covers essential concepts, classical ML algorithms, and recent advancements in the field. Participants will gain hands-on experience with frameworks like scikit-learn, TensorFlow/Keras, XGBoost, DNN, CNN, RNN, and more.

Objectives

To provide an introduction to the fundamentals of Machine Learning and its applications.
To equip participants with essential skills for data preprocessing and feature engineering.
To introduce various machine learning algorithms, including clustering, boosting, and decision trees.
To explore advanced topics such as DNN, CNN, RNN, and Transformer using TensorFlow/Keras Library.
To demonstrate practical implementation through assignments and projects in applied machine learning.

Prerequisite

We expect participants to have prior programming knowledge, specifically in Python. If you lack this background, please learn the basics of Python before starting this course. This course does not cover Python fundamentals, and enrolling without adequate Python knowledge may lead to significant difficulties in understanding the content, resulting in a poor learning experience. This responsibility lies solely with the participant. We have also offered an "Introduction to Python" course (Course Details Link), which you can complete prior to enrolling in this course.

Tentative Class Schedule

The course length will be 8 weeks with two classes in each week and 3 hours in each class. The tentative lecture plan of the course is as follows:

Class#	Content
1	Introduction to Machine Learning, Data Preprocessing and Feature Engineering
2	Introduction to scikit-learn and Model Building Basics
3	Linear Regression and Model Evaluation Metrics
4	Logistic Regression and Classification Metrics
5	Clustering Techniques: K-Means, Hierarchical Clustering
6	Decision Trees and Random Forests
7	Boosting Techniques: AdaBoost, Gradient Boosting, XGBoost
8	Support Vector Machines (SVM) and Kernel Methods
9	Evaluation of Machine Learning Models (Cross-validation, overfitting, learning curve, over sampling/under sampling, etc.)
10	Ensemble Learning Techniques
11	Introduction to Neural Networks: Deep Neural Network (DNN)
12	Convolutional Neural Network (CNN) and Hands-on Practice
13	Recurrent Neural Network (RNN) and Sequence Modeling
14	Transformer Models, Large Language Models (LLMs)
15	Introduction to Transfer Learning and Advanced Topics in Neural Networks
16	Final Exam

Learning and Evaluation Method

Classes will be conducted in a multimedia-equipped environment.
Expert faculty members from the field of Machine Learning will lead each class.
All instructors are faculty members from the Department of CSE, BUET.
Participants will have access to PCs for practical exercises, ensuring an interactive learning experience.
An evaluation will take place through assignments and a final exam at the end of the course.
We will provide a certificate upon successfully passing this course.

Further Query

Email: iac@cse.buet.ac.bd
Phone: 9665650-80 Ext-6438
Mobile: 01670032959