Machine Learning With Python – Online Training Course Topics

1. Basics of Statistics

1. Descriptive Statistics

• Measures of Central Tendency (Averages):
  • Mean
  • Median
  • Mode
• Measures of Dispersion:
  • Range
  • Percentiles, Quartiles, Interquartile Range (IQR)
  • Variance
  • Standard Deviation
• Measures to Describe the Shape of Distribution:
  • Skewness
  • Kurtosis

2. Measures of Correlation

• Correlation:
  • Importance of Correlation
  • Types of Correlation
  • Degree of Correlation
• Methods to Measure Correlation:
  • Scatter Diagram
  • Karl Pearson’s Coefficient of Correlation
  • Spearman’s Rank Correlation Coefficient

3. Probability for Statistics

• Types of Events:
  • Independent Events
  • Dependent Events
  • Mutually Exclusive Events
  • Inclusive Events
• Types of Probability:
  • Marginal Probability
  • Joint Probability
  • Conditional Probability
• Bayes Theorem

4. Inferential Statistics

• Estimation
• Hypothesis Testing

5. Probability Distributions

• Discrete Distributions:
  • Uniform Distribution
  • Binomial Distribution
  • Poisson Distribution
• Continuous Distributions:
  • Exponential Distribution
  • Normal Distribution (Gaussian Distribution) (Bell Curve)
  • Standard Normal Distribution (Z-distribution)
  • Student’s T-Distribution

2. Introduction to Python Libraries for Data Science

• NumPy: Numerical Computing
• Pandas: Data Manipulation
• Matplotlib: Data Visualization
• Seaborn: Statistical Data Visualization

3. Introduction to Artificial Intelligence and Machine Learning

• Overview of AI and ML: Foundations of AI and its capabilities.
• Applications of AI: Real-world use cases of Artificial Intelligence.
• AI Project Life Cycle: Key stages in the development and deployment of AI projects.
• Types of Learning:
  • Supervised Learning: Predict outcomes using labeled data.
  • Unsupervised Learning: Discover patterns without labels.
  • Semi-Supervised Learning: Leverage labeled and unlabeled data.
  • Reinforcement Learning: Learn optimal actions using rewards.
• AI Ethics and Bias: Ensuring fairness and reducing bias in AI systems.

4. Foundations of Machine Learning

• Steps to Build an ML Model: End-to-end ML model creation process.
• Overfitting vs Underfitting: Balancing model complexity for better predictions.
• Data Preprocessing: Handling missing values, outliers, and noisy data.
• Evaluation Metrics:
  • Regression Metrics: MAE, MSE, R2 Score.
  • Classification Metrics: Accuracy, Precision, Recall, F1-Score.

5. Supervised Learning

• Regression Algorithms:
  • Linear Regression, Polynomial Regression.
  • Ridge Regression (L2 Regularization), Lasso Regression (L1 Regularization).
  • ElasticNet Regression (L1 and L2 Regularization).
• Classification Algorithms:
  • Decision Tree, Random Forest, SVM.
  • Naive Bayes, K-Nearest Neighbors (KNN).
• Advanced Topics: Handling imbalanced data and class weighting.

6. Unsupervised Learning

• Clustering:
  • K-Means Clustering, Hierarchical Clustering.
  • DBSCAN (Density-Based Spatial Clustering of Applications with Noise).
• Dimensionality Reduction:
  • Principal Component Analysis (PCA), t-SNE (t-Distributed Stochastic Neighbor Embedding).
• Association Rule Mining:
  • Apriori Algorithm, F-P Growth Algorithm.
• Anomaly Detection:
  • Isolation Forest, One-Class SVM.
• Advanced Clustering: Spectral Clustering and Affinity Propagation.

7. Feature Engineering

• Encoding Techniques:
  • Label Encoding, One-Hot Encoding.
  • Count Encoding, Mean Encoding, Weight of Evidence Encoding.
• Feature Interaction: Creating new features from existing data.
• Datetime Functions: Extracting useful features from time data.
• Text Features: Tokenization and text vectorization (e.g., Word2Vec).

8. Feature Selection

• Filter Methods: Removing irrelevant features based on metrics.
• Wrapper Methods:
  • Forward Selection, Backward Elimination.
  • Recursive Feature Elimination (RFE).
• Embedded Methods:
  • Ridge Regression, Lasso Regression, ElasticNet.
  • Decision Tree-Based Methods (e.g., Random Forest, XGBoost, LightGBM).

9. Optimization and Model Building

• Loss Functions: Quantifying the error in predictions.
• Gradient Descent:
  • Batch Gradient Descent, Stochastic Gradient Descent (SGD).
  • Mini-Batch Gradient Descent.
• Hyperparameter Optimization:
  • Grid Search, Random Search, Bayesian Optimization.
• Model Tuning: Fine-tuning hyperparameters for improved accuracy.

10. Advanced Techniques

• Ensemble Learning:
  • Bagging: Random Forest and Bootstrap Aggregation.
  • Boosting: Gradient Boosting Machines (GBM), XGBoost, LightGBM, CatBoost.
• Transfer Learning: Reusing pretrained models for new tasks.
• Time Series Analysis:
  • ARIMA and SARIMA Models, Prophet for Forecasting.
  • Feature Engineering for Time Series Data.

11. Explainability and Interpretability

• SHAP (SHapley Additive exPlanations): Explaining feature impacts on predictions.
• LIME (Local Interpretable Model-agnostic Explanations): Simplifying complex models for human interpretation.
• Advanced Tools: Counterfactual Explanations and Saliency Maps.

12. Model Deployment and Real-World Applications

• Tools for Deployment:
  • Deploying with Flask, Django, Streamlit.
• APIs and Endpoints: Building interfaces for model access.
• Real-World Application Projects: End-to-end deployment of ML solutions.

13. Ethics and Governance in AI

• AI Fairness and Transparency: Ensuring equitable AI decisions.
• Bias Mitigation Techniques: Strategies to reduce biases in AI systems.
• Ethical Use Cases: Real-world examples addressing ethical challenges.

14. End-of-Course Projects

• Hands-on Real-World Applications:
  • Predictive Modeling.
  • Customer Segmentation (Clustering).
  • Fraud Detection (Anomaly Detection).
  • Time Series Forecasting.
  • Model Deployment Project.