Machine-Learning-Data-Science-and-AI-Engineering-with-Python

Section	Resource	Description
Chapter 1	Titanic - Your first Machine Learning model	Your first Machine Learning model - a classification model
Chapter 2	King County House Sales Prediction	Build a regression model with LinearRegression
Chapter 3	Customer Segmentation and Churn Prediction	Perform Customer Segmentation using K-Means and Predict Customers Churn
Chapter 4	Embeddings & FeatureHasher IEEE-CIS Fraud Detection	Embeddings in PyTorch and Feature Hasher IEEE-CIS Fraud Detection Solution to illustrate feature engineering
Chapter 5	Define a LTU with PyTorch Implement Perceptron in PyTorch Simple MLP in PyTorch House Prices Solution with PyTorch	Define AND & OR LTU gates Implement Perceptron from scratch in PyTorch Simple MLP in PyTorch A Regression Nodel for House Prices Solution with PyTorch
Chapter 6	Model W&B initialization Simple PyTorch Lightning Example Titanic Solution using PyTorch	Model Weights & Biases initialization in PyTorch Simple Implementation of a Model for Iris Dataset using PyTorch Lightning Titanic Competition Solution using PyTorch
Chapter 7	MNIST Solution using PyTorch Fashion-MNIST Solution	Solution of MNIST using PyTorch Fashion-MNIST Solution with train/valid split, Batch Normalization and Dropout
Chapter 8	Self-Attention from Scrath Fine-Tune BERT for Multiclass Text Classification Fine-Tune BERT for a Sentiment Analysis Task	Build a self-attention module from scratch Fine-Tune BERT for Multiclass Text Classification from AG News Fine-Tune BERT for a Sentiment Analysis Task using Financial data
Chapter 9	User-based collaborative filtering User-based collaborative filtering (MovieLens) Item-based collaborative filtering (MovieLens) Content-based recommender system (MovieLens) Hybrid recommender system (MovieLens)	User-based collaborative filtering User-based collaborative filtering using MovieLens Item-based collaborative filtering using MovieLens Content-based recommender system using MovieLens Hybrid recommender system using MovieLens
Chapter 10	Explaining a Credit-Scoring Model with PyTorch	Model explainability techniques for a credit scoring model
Chapter 11	Fashion MNIST Solution Fashion MNIST Solution & TensorBoard Fashion MNIST Solution & MLflow Fashion MNIST Solution & Optuna Fashion MNIST Solution & Ray Tune Optimization and experiment tracking	Initial solution for Fashion-MNIST with PyTorch - modified for easy parameterization Use TensorBoard for local training inspection Experiment tracking with MLflow Hyperparameter optimization with Optuna Scalling Hyperparameter optimization with Ray Tune End-to-end project with Optuna & MLflow
Chapter 12	Train, Deploy, Serve, and Monitor a ML Solution	Train a PyTorch model, deploy the inference service using FastAPI and Docker, monitor the service using Prometheus
Chapter 13	Scalling, automation, and MLOps pipeline	Train a custom model, monitor model performance and trigger retraining
Chapter 14	Train a GAN to generate new handwritten digits	Generative Models and Autoencoders: Train a GAN to generate new handwritten digits
Chapter 15
Chapter 16
Chapter 17