University of Global Village (UGV), Barishal.
Lesson Plan: CSE Lab Courses
Course Name AI-ML-DS
Course Code CSE
Semester 5th
Course Level 01
Supervisor Md. Minhaj Ul Islam
Instructor/Assistant Ahad Khan
Lesson Lesson Title Lesson Details Remarks
No
1. Introduction to AI, ML, Understand the fundamental differences
DL & Data Science between AI, Machine Learning (ML), Deep
Learning (DL), and Generative AI. Explore
real-world applications of these
technologies. Set up the development
environment and install essential tools.
2. Python & Important Learn Python basics, syntax, and essential
Libraries libraries such as NumPy, Pandas, and
Matplotlib. Practice implementing these
libraries to manipulate and visualize data.
3. Data Collection & Differentiate between structured and
Handling unstructured data. Explore data collection
techniques, including web scraping, APIs,
and loading datasets from CSV files.
4. Data Wrangling & Learn to handle missing values, remove
Preprocessing duplicates, and encode categorical variables.
Clean and preprocess raw datasets to make
them ML-ready.
5. Exploratory Data Analysis Analyze datasets using key statistics like
(EDA) & Feature mean, median, and correlation. Learn
Engineering feature selection and extraction techniques
University of Global Village (UGV), Barishal.
to improve model performance.
6. Introduction to Machine Understand the differences between
Learning supervised and unsupervised learning. Get
an overview of popular ML algorithms and
train your first ML model.
7. Model Optimization Learn the mechanics of gradient descent,
compare stochastic and batch gradient
descent, and explore loss and cost functions.
8. Regression Models Explore linear regression and understand
(Prediction Tasks) - Part 1 overfitting vs. underfitting concepts. Train a
regression model to predict house prices.
9. Regression Models Learn about Ridge and Lasso regression
(Prediction Tasks) - Part 2 techniques. Evaluate model performance
using MSE and RMSE metrics.
10. Classification Models Understand logistic regression and decision
(Decision Making) trees. Learn how to evaluate classification
models using precision, recall, and F1 score.
11. Advanced ML - Ensemble Explore ensemble methods like Random
Learning Forest and Gradient Boosting to improve
model accuracy.
12. Clustering & Understand unsupervised learning methods
Dimensionality Reduction such as K-Means clustering and Principal
Component Analysis (PCA). Apply these
techniques for customer segmentation.
13. End-to-End ML Pipeline Learn about feature selection, model
selection, and hyperparameter tuning. Train
an ML model and evaluate its performance
using real-world data.
14. Neural Networks Basics - Understand the perceptron model and
Part 1 forward propagation. Build a simple neural
network up to the forward propagation
stage.
15. Neural Networks Basics - Learn about backpropagation and loss
functions. Complete the implementation of
University of Global Village (UGV), Barishal.
Part 2 a simple neural network.
16. Deep Learning with Explore deep learning frameworks and
TensorFlow/PyTorch/Ker activation functions. Train a neural network
as using TensorFlow, PyTorch, or Keras.
17. Convolutional Neural Understand CNN architectures, including
Networks (CNNs) filters and pooling. Train a CNN for image
classification.
18. Transfer Learning Use pretrained models like ResNet, VGG,
(Pretrained Models) and EfficientNet for custom image
classification tasks.
