Build and deploy ML models.
Machine Learning — the ML workflow, NumPy and pandas, feature engineering, regression and classification, evaluation, unsupervised learning, tuning and pipelines, an introduction to deep learning, and model deployment with Python and scikit-learn. Every course carries 10 hands-on exercises with solutions.
Model Tuning & Pipelines
Build production-quality, reproducible models with scikit-learn by tuning hyperparameters correctly and wrapping every preprocessing step and estimator inside a single Pipeline. You will learn to search the hyperparameter space with cross-validation, avoid data leakage, and persist the best model for deployment.
Introduction to Deep Learning
Build your first neural network from the ground up — understand neurons, layers and activations, see how forward pass and backpropagation actually work, and train a real model in Keras/TensorFlow. You will finish able to design, train and validate a simple network on both tabular and image data, and judge when deep learning is genuinely worth it.
Deploying Machine Learning Models
Take a trained scikit-learn model out of a notebook and serve it to real users as a reliable HTTP prediction service. You will persist models with joblib, wrap them in Flask and FastAPI endpoints, validate inputs, choose between batch and real-time inference, and version, monitor and containerise the result with basic MLOps practice.