ByteToCode
ByteToCode Special Batch
Machine Learning And
Deep Learning With
Research Applications
Swipe for more
COURSE OVERVIEW
Duration: 3 months (12 weeks)
Classes/week: 2 (24 total sessions)
Session Length: 1.5–2 hours
Delivery Mode: Live + Projects + Assignments + Quiz
Class Starts: Last Week of August
OUR INSTRUCTOR
Md. Reja E Rabbi Tonmoy
[Link]. in CSE, [Link]. in CSE at BUET
Machine Learning Engineer, Pathao Ltd.
Research Fellow,ICT Ministry Bangladesh
Research Assistant, Sol Asia
Former Lecturer,Dept. of CSE,NUB
Former Software Developer,ICT Cell,BUET
Module 1:
(Sessions 1-2)
Python for Data Science & ML
Foundations
Introduction to ML & DS, Types of ML
CRISP-DM Framework
Python Basics for ML (Variables, Loops,
Data Types, Functions, Lists, Dictionaries,
Parameters/Arguments)
1 Assignment 1 quiz
Module 2:
(Sessions 3-4)
Python for Data Science & ML
Foundations
NumPy & Pandas for Data Manipulation
Data Cleaning, Missing Value Handling
Numpy Essentials (Basics, Arrays, Init, max, min,
argmax, argmin)
Pandas Essentials (Intro, Series, Create, DataFrame,
Data Structure)
1 Assignment 1 quiz
Module 3:
(Sessions 5-6)
Python for Data Science & ML
Foundations
Data Types & Central Tendency: Qualitative & Quantitative
Data, Mean, Median, Mode
Statistical Measures: Variance, Standard Deviation, Normal
Distribution, Correlation
Intro to Exploratory Data Analysis (EDA)
Time Series Data, Geo-spatial Data, Multidimensional Data,
Comparative Data Visualization, Visual Analytics
1 Assignment 1 quiz
Module 4:
(Sessions 7-8)
Python for Data Science & ML
Foundations
Feature Extraction
Outliers Detection with Standard Deviation & Z Score
Feature Engineering and Linear Engineering:
Encoding, Scaling
Project 1 Kickoff: Car Price Prediction
1 Assignment 1 quiz
Car Price Prediction Project
Roadmap
1. Car price prediction project 10. Using RMSE on validation data
2. Data preparation 11. Feature engineering
3. Exploratory data analysis 12. Categorical variables
4. Setting up the validation framework 13. Regularization
5. Linear regression 14. Tuning the model
6. Linear regression: vector form 15. Using the model
7. Training linear regression: Normal equation 16. Car price prediction project summary
8. Baseline model for car price prediction 17. Explore more
9. Root mean squared error 18. Homework
Module 5:
(Sessions 9-10)
Python for Data Science & ML
Foundations
Regression (Simple, Multiple, Regularization)
Model Evaluation (RMSE, MSE, MAPE, MAE, R²,
Recall/Sensitivity)
Project 1 Wrap-up
1 Assignment 1 quiz
Module 6:
(Sessions 11-12)
Core ML Algorithms & Domain
Applications
Logistic Regression (Theory & Implementation)
Classification Metrics: Confusion Matrix, Precision,
Recall, F1-Score, ROC-AUC
Churn Prediction Project Setup
Project 2 Kickoff: Churn Prediction (Classification)
1 Assignment 1 quiz
Churn Prediction Project
Roadmap
1. Churn prediction project 8. One-hot encoding
2. Data preparation 9. Logistic regression
3. Setting up the validation framework 10. Training logistic regression with
4. EDA Scikit-Learn
5. Feature importance: Correlation 11. Model interpretation
6. Feature importance: Mutual information 12. Using the model
7. Feature importance: Churn rate and risk 13. Summary
ratio 14. Explore more
15. Homework
Module 7:
(Sessions 13-14)
Core ML Algorithms & Domain
Applications
K-Nearest Neighbors (KNN) – Theory & Scikit-Learn
Implementation
Support Vector Machines (SVM) – Linear & RBF Kernels
Hyperparameter Tuning (GridSearchCV)
1 Assignment 1 quiz
Module 8:
(Sessions 15-16)
Core ML Algorithms & Domain
Applications
Introduction to Biomedical ML
Project 3 Kickoff: Predicting Disease Outcomes from
Medical Data (e.g., Heart Disease, Diabetes dataset)
Ethical AI in Healthcare Discussion
1 Assignment 1 quiz
Module 9:
(Sessions 17-18)
Core ML Algorithms & Domain
Applications
Decision Trees – Splitting Criteria & Pruning
Random Forest – Bagging, Feature Importance
Project Wrap-Up + Mid-course Quiz
1 Assignment 1 quiz
Module 10:
(Sessions 19-20)
Deep Learning, NLP & CV
Neural Networks Basics, Gradient descent, and
how neural networks learn.
TensorFlow & Keras Setup
Project 4 Kickoff: NLP – Sentiment Analysis on
Tweets or Medical Text
1 Assignment 1 quiz
Module 11:
(Sessions 21-22)
Deep Learning, NLP & CV
CNN Basics & Image Classification From Scratch
Project 5 Kickoff: Computer Vision – Pneumonia
Detection from X-rays
1 Assignment 1 quiz
Module 12:
(Sessions 23-24)
Deep Learning, NLP & CV
Transfer Learning (ResNet, BERT basics )
Back-propagation
Project Work:
1. Natural Language Processing (NLP)
2. (BERT or LSTM) & CV (Pre-trained CNNs)
1 Assignment 1 quiz
Module 13:
(Bonus)
Model Deployment (Flask, Docker, AWS)
Final Project Presentations
Research Roadmap: How to Read Papers,
Design Experiments, Publish Work
1 Assignment 1 quiz
ByteToCode
Join our Special Batch
Machine Learning And
Deep Learning With
Research Applications
For Inquiry
Email: [Link]@[Link] Phone: 01797623424