Applied Machine Learning, Deep Learning & NLP
with Python
Instructor: MD. Asif Mredha
Managing Director, Kryzotech
Machine Learning Trainer, Hamdard University Bangladesh
Former Data Scientist, Nighthawk
Former Data Science Trainer, Microland IT Institute
Course Architect: "Big Data, Data Analytics, and Data Science" – SEIP (Govt. Project)
🎓 Course Structure (Total: 40 Classes)
📦 Module 1: Introduction to Machine Learning (1 Class)
Class 1:
Overview of Machine Learning & Industry Use Cases
Roadmap to Become a Machine Learning Engineer
Real-World Applications
🐍 Module 2: Python for Machine Learning (6 Classes)
Class 1: Python Basics: Syntax, Variables, Data Types, Operators, Casting, Input, Comments
Class 2: Data Structures (List, Tuple, Set, Dictionary), Control Flow (If-Else, Loops), Problem-
Solving
Class 3: Looping (For, While), Python Statements (pass, continue, break), Functions, Lambda,
Math Module, Array
Class 4: OOP Basics: Classes, Objects, Inheritance, Iterators, Exception & File Handling
Class 5: Recap + Integrative Problem Solving
Class 6: Final Python Problem-Solving Class
🔢 Module 3: Numerical Computing & Data Manipulation (3 Classes)
Class 1: NumPy: Arrays, Indexing, Reshaping, Mathematical Ops, Joins, Splits
Class 2: Pandas: DataFrames, Importing, Cleaning, Filtering, Sorting, Merging, Missing Values
Class 3: Real-World Data Practice with Pandas
📊 Module 4: Data Visualization (3 Classes)
Class 1: Matplotlib: Line, Bar, Scatter, Histogram, Pie, Customization
Class 2: Seaborn: Relational, Categorical, and Distribution Plots, Countplot, Swarmplot, Real
Dataset Plotting
Class 3: Data Visualization Project
🧹 Module 5: Data Preprocessing (3 Classes)
Class 1: Data Preprocessing Techniques – Part 1
Class 2: Data Preprocessing Techniques – Part 2
Class 3: Real-World Preprocessing Project
🧾 Module 6: Version Control with Git & GitHub (1 Class)
Class 1: Git & GitHub: Repository Setup, Push/Pull, Collaboration
📈 Module 7: Statistics for Machine Learning (2 Classes)
Class 1: Descriptive & Inferential Statistics
Mean, Median, Mode, Variance, Std Dev, Skewness, Kurtosis
Histograms, Boxplots
Probability Basics: Normal, Binomial, Poisson Distributions
Central Limit Theorem, Confidence Intervals
Class 2: Hypothesis Testing & Correlation
Null/Alternative Hypothesis, p-value, Type I/II errors
t-test, z-test, ANOVA, Chi-Square Test
Pearson & Spearman Correlation, Covariance
Feature Selection, Multicollinearity, Statistical Significance in ML
🗃️ Module 8: Database for Machine Learning (2 Classes)
Class 1: SQL & Relational Databases
Tables, Keys, Schemas
SELECT, WHERE, GROUP BY, HAVING, JOINs
Connecting Jupyter with MySQL
Class 2: Querying for Machine Learning
Subqueries, CASE, Nested Queries
Window Functions (ROW_NUMBER, RANK)
ETL Basics, Dataset Preparation from SQL for ML Projects
🤖 Module 9: Machine Learning (8 Classes)
Class 1: Machine Learning Algorithm
Class 2: Machine Learning Algorithm
Class 3: Supervised Learning: Model Building(Regression), Model Evaluation for
regression
Class 4: Supervised Learning: Model Building(Classification) , Model Evaluation for
classification
Class 5: Unsupervised Learning: Clustering (K-Means, K-Modes, Hierarchical)
Class 6: Unsupervised Learning: PCA, Market Basket Analysis
Class 7: Hyperparameter Tuning, overfitting check, Data distribution check, Implement
hypothesis testing
Class 8: Project Discussion
🧠 Module 10: Natural Language Processing (3 Classes)
Class 1: Preprocessing (Tokenization, Stopwords, Stemming, Lemmatization), Bag of Words,
TF-IDF, Word2Vec
Class 2: NLP Projects in English: Sentiment Analysis, Fake News Detection, Bullying Detection
Class 3: NLP Projects in Bangla: Comment Classification, Article Classification
🧠 Module 11: Deep Learning (5 Classes)
Class 1: Intro to ANN, CNN, RNN + Use Cases in ML
Class 2: TensorFlow & Keras Basics, ANN for Structured Data
Class 3: CNN for Image Classification (CIFAR-10, Brain MRI)
Class 4: CNN (Handwritten dataset, Customized dataset: Face Recognition), Fine-Tuning &
Augmentation
Class 5: RNN/LSTM for Text Generation, Sequence Modeling, NLP Deep Learning Project
🌐 Module 12: Model Deployment & Web Framework (1 Class)
Class 1: Flask API, Streamlit UI, Model Deployment (ML & DL Projects)
🚀 Module 13: Final Project & Presentation (2 Classes)
Class 1: Final Project Planning, Dataset Selection, Model Building
Class 2: Final Presentation + Deployment Showcase
✅ Certification Requirement:
Students must submit three completed projects, including the final project, to be eligible for
the Certificate of Completion.
