Full Stack Machine Learning

By the end of this course, you will have a solid foundation in machine learning techniques and practical skills to apply them to real-world problems. Get ready to unlock the potential of data and make intelligent predictions using machine learning algorithms!

Week 1: Python for Machine Learning Foundation

• Basics of Python Programming Language **RECAP**
• Numpy Fundamentals: Basic refresher on linear algebra and calculus for machine learning & deep learning. **RECAP**
• Exploratory Data Analysis & Hypothesis Testing **RECAP**
• Assignment/Quiz

Week 2: Introduction to Machine Learning

• Overview of Machine Learning concepts, types, and application
• Supervised Learning
• Regression: Linear regression, and evaluation metrics
• Assignment/Quiz

Week 3: Logistic Regression and Classification

• Classification: Logistic regression and evaluation metrics
• K-nearest Neighbors
• Support Vector Machines
  Capstone project: Students will work on a capstone project that integrates the concepts and techniques covered throughout the curriculum starting from week 3 to 12.

Week 4: Decision Trees and Ensemble Methods

• Ensemble Methods: Decision trees, random forests, gradient boosting, and bagging.
• Feature importance and interpretation
• XAI – Explainable Artificial Intelligence: SHAP (SHapley Additive exPlanations): Using cooperative game theory to allocate contributions of each feature to the final prediction.
  Capstone project

Week 5: Model selection and regularization

• Model Selection and Regularization: Bias-Variance Tradeoff, Cross-validation, and regularization techniques.
• Hyperparameter Tuning: Grid search, randomized search, and Bayesian optimization.
• Building an end-to-end Machine Learning pipelines
• Experiment Tracking
  Capstone project

Week 6: Unsupervised Learning

• Clustering: K-Means and DBSCAN.
• Dimensionality Reduction: Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE)
  Capstone project

Week 7: Sentiment Analysis

• Text Preprocessing: Cleaning, tokenization, and normalization.
• Analyzing and interpreting sentiment in text data using various machine learning approaches.
• Classification: Techniques for classifying text data, with Naive Bayes
• Topic Modelling
  Capstone project

Week 8: Recommender Systems

• Types of Recommender Systems
• Content-Based Filtering: Feature extraction, similarity measures, and item profiles.
• Collaborative Filtering: Memory-based CF and model-based CF.
  Capstone project

Week 9: Introduction to Deep Learning with PyTorch

• Tensors and Autograd.
• Introduction to Neural Networks: Forward and backpropagation, gradient descent.
• Building a Simple Neural Network: Multi-Layer Perceptron (MLP).
  Capstone project

Week 10:

• Recurrent Neural Networks (RNN)
• Convolutional Neural Networks (CNN)
• Image Classification using CNN
  Capstone project

Week 11: Model Deployment

• MLOps Overview
• Types of Model Deployment.
• Basics of deploying machine learning models using frameworks like
• FastAPI and Streamlit.
  Capstone project

Week 12:

• Deploying a ML Model with FeatureStore
• End-to-end ML project with model deployment
  Capstone project review