Home / Machine Learning Classes

Machine Learning Classes

Course Content : Machine Learning

Level 1: Basic Machine Learning Syllabus

1. Introduction to Machine Learning

  • Definition and scope of ML
  • Types of ML: Supervised, Unsupervised, Reinforcement
  • ML applications in real-world domains
  • Overview of ML workflow (data → model → evaluation → deployment)

2. Mathematics Foundation

  • Linear algebra (vectors, matrices, dot product, transpose)
  • Probability basics (conditional probability, Bayes theorem)
  • Statistics basics (mean, median, variance, standard deviation)

3. Data Handling

  • Data formats and datasets
  • Data cleaning (handling missing values, duplicates, outliers)
  • Feature scaling (normalization, standardization)
  • Train/test/validation splits

4. Supervised Learning Basics

  • Linear Regression (simple & multiple)
  • Logistic Regression
  • k-Nearest Neighbors (k-NN)
  • Decision Trees
  • Naïve Bayes Classifier

5. Unsupervised Learning Basics

  • k-Means Clustering
  • Hierarchical Clustering
  • Principal Component Analysis (PCA)

6. Model Evaluation & Validation

  • Confusion matrix, accuracy, precision, recall, F1-score
  • Cross-validation
  • Bias-variance tradeoff

7. Tools & Libraries

  • Python basics for ML
  • NumPy, Pandas, Matplotlib, Seaborn
  • scikit-learn basics

Level 2: Advanced Machine Learning Syllabus

1. Advanced Data Preparation

  • Feature engineering (interaction features, encoding, binning)
  • Dimensionality reduction (PCA, t-SNE, LDA)
  • Imbalanced data handling (SMOTE, undersampling, oversampling)

2. Advanced Supervised Learning

  • Support Vector Machines (SVM)
  • Ensemble methods: Bagging, Boosting (AdaBoost, XGBoost, LightGBM, CatBoost)
  • Random Forests
  • Gradient Boosting Machines

3. Advanced Unsupervised Learning

  • DBSCAN
  • Gaussian Mixture Models (GMM)
  • Self-Organizing Maps (SOM)

4. Time Series Analysis

  • Stationarity and differencing
  • ARIMA, SARIMA models
  • Prophet library basics
  • LSTM for time series forecasting

5. Neural Networks & Deep Learning Introduction

  • Perceptrons, activation functions
  • Feedforward Neural Networks
  • Backpropagation
  • Overfitting & regularization (dropout, early stopping)
  • Introduction to CNNs and RNNs

6. Model Optimization & Deployment

  • Hyperparameter tuning (Grid Search, Random Search, Bayesian Optimization)
  • Model versioning
  • Model deployment basics (Flask, FastAPI, Docker)

7. Advanced Topics

  • Transfer Learning
  • Generative models (GANs basics)
  • Autoencoders
  • Reinforcement Learning basics (Q-learning, policy gradients)

8. Tools & Frameworks

  • scikit-learn advanced usage
  • TensorFlow, PyTorch
  • MLflow for experiment tracking
  • Streamlit for interactive ML apps