1
Python for Machine Learning
Python basics, NumPy, Pandas, Matplotlib & Seaborn, Jupyter, virtual environments, Git & version control.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Refresh Python basics
• Use NumPy and Pandas for data
• Visualize with Matplotlib & Seaborn
• Work in Jupyter and virtual environments
• Apply Git & version control
2
Mathematics for ML
Linear algebra (vectors, matrices, eigenvalues), calculus (derivatives, gradient), probability (distributions, Bayes), statistics (mean, variance, hypothesis testing, CLT).
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Apply linear algebra for ML
• Use calculus (derivatives, chain rule, gradient)
• Apply probability and Bayes theorem
• Use statistics: mean, variance, covariance, hypothesis testing, CLT
3
Data Preprocessing & EDA
Data cleaning, missing values, outliers, feature scaling, encoding, feature engineering, EDA, visualization best practices.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Clean data and handle missing values
• Detect outliers and scale features
• Encode categorical variables
• Perform feature engineering
• Conduct EDA and apply visualization best practices
4
Introduction to Machine Learning
What is ML, types (supervised, unsupervised, semi-supervised, reinforcement), ML pipeline, bias-variance tradeoff.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Define ML and its types
• Understand supervised, unsupervised, semi-supervised, reinforcement learning
• Build ML pipeline
• Understand bias-variance tradeoff
5
Supervised Learning – Regression
Linear, multiple linear, polynomial regression; Ridge, Lasso, ElasticNet; MAE, MSE, RMSE, R².
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Implement linear, multiple linear, polynomial regression
• Apply Ridge, Lasso, ElasticNet
• Use MAE, MSE, RMSE, R²
6
Supervised Learning – Classification
Logistic regression, KNN, Naive Bayes, SVM, Decision Trees, Random Forest, Gradient Boosting, XGBoost, LightGBM, CatBoost; confusion matrix, precision, recall, F1, ROC-AUC.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Apply logistic regression, KNN, Naive Bayes, SVM
• Use decision trees, Random Forest, gradient boosting, XGBoost, LightGBM, CatBoost
• Evaluate with confusion matrix, precision, recall, F1, ROC-AUC
7
Model Evaluation & Tuning
Train/test split, K-fold cross validation, hyperparameter tuning (grid search, random search), overfitting/underfitting, feature importance.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Use train/test split and K-fold cross validation
• Tune hyperparameters with grid and random search
• Address overfitting and underfitting
• Interpret feature importance
8
Unsupervised Learning
K-Means, hierarchical clustering, DBSCAN, PCA, t-SNE, association rules (Apriori).
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Apply K-Means, hierarchical clustering, DBSCAN
• Use PCA and t-SNE for dimensionality reduction
• Apply association rule learning (Apriori)
9
Ensemble Methods
Bagging, boosting, stacking, voting classifiers, advanced gradient boosting.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Apply bagging, boosting, stacking
• Use voting classifiers
• Apply advanced gradient boosting
10
Feature Engineering & Selection
Feature transformation, interaction features; filter, wrapper, embedded methods; dimensionality reduction.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Transform features and create interaction features
• Apply filter, wrapper, embedded selection methods
• Use dimensionality reduction
11
Time Series Analysis
Time series components, ARIMA, SARIMA, Prophet, forecasting models, evaluation metrics.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Understand time series components
• Apply ARIMA, SARIMA, Prophet
• Build forecasting models and evaluate them
12
Anomaly Detection
Statistical methods, Isolation Forest, One-Class SVM, real-world use cases.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Apply statistical methods for anomaly detection
• Use Isolation Forest and One-Class SVM
• Solve real-world use cases
13
Neural Network Fundamentals
Perceptron, activation functions, backpropagation, loss functions, gradient descent variants.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Understand perceptron and activation functions
• Apply backpropagation and loss functions
• Use gradient descent variants
14
Deep Learning Frameworks
TensorFlow, Keras, PyTorch, model training workflow.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Use TensorFlow, Keras, PyTorch
• Follow model training workflow
15
Computer Vision
CNN architecture, image classification, object detection, transfer learning, image augmentation.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Design CNN architecture
• Perform image classification and object detection
• Apply transfer learning and image augmentation
16
Natural Language Processing (NLP)
Text preprocessing, tokenization, word embeddings, RNN & LSTM, Transformers, BERT, sentiment analysis, text classification.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Preprocess text and tokenize
• Use word embeddings, RNN, LSTM
• Apply Transformers and BERT
• Perform sentiment analysis and text classification
17
Generative AI & Large Language Models
Transformers architecture, GPT models, prompt engineering, fine-tuning, RAG, LLM deployment.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Understand Transformers and GPT models
• Apply prompt engineering and fine-tuning
• Use RAG and deploy LLMs
18
Reinforcement Learning
Markov Decision Process, Q-Learning, policy gradient, Deep Q Networks.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Model problems with MDP
• Apply Q-Learning and policy gradient
• Use Deep Q Networks
19
Model Deployment
Flask/FastAPI, REST APIs, Docker, model serialization, CI/CD basics.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Deploy with Flask/FastAPI and REST APIs
• Use Docker and model serialization
• Apply CI/CD basics
20
MLOps
ML pipelines, model monitoring, drift detection, experiment tracking, MLflow, DVC.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Build ML pipelines and monitor models
• Detect drift and track experiments
• Use MLflow and DVC
21
Cloud for ML
AWS for ML, GCP AI Platform, Azure ML, model hosting, AutoML.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Use AWS, GCP, Azure for ML
• Host models and apply AutoML
22
ML System Design
End-to-end ML pipeline design, data architecture, feature store, scalable inference.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Design end-to-end ML pipeline
• Plan data architecture and feature store
• Design scalable inference
23
Responsible AI
Bias & fairness, model explainability (SHAP, LIME), ethical AI, data privacy.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Address bias and fairness
• Apply explainability (SHAP, LIME)
• Consider ethical AI and data privacy
24
Real-World Projects
Customer churn, fraud detection, recommendation system, stock prediction, NLP chatbot, computer vision app.
Locked
Please enroll in this course to access the modules.
Learning objectives:
• Build customer churn prediction
• Implement fraud detection and recommendation system
• Build stock prediction, NLP chatbot, computer vision app