Writing

I spent more time than I'd like to admit computing ad - bc without knowing what the number meant. It's the signed area of a parallelogram. Once I saw that, everything else in this topic stopped feeling like a list of rules to memorize.

Drag vectors, warp grids, and discover that a 2×2 grid of numbers is secretly a transformation machine. An interactive visual essay on rotation, scaling, shearing, and the geometry hiding inside every matrix.

A comprehensive guide to implementing security best practices in ML pipelines using Amazon SageMaker, covering data protection, access control, and monitoring strategies for production ML systems.

Learn how to build and train image classification models using TensorFlow within Amazon SageMaker. This hands-on guide covers the complete workflow from data preparation to model deployment.

Step-by-step tutorial on training and deploying scikit-learn models using Amazon SageMaker. Perfect for data scientists looking to leverage AWS cloud infrastructure for ML workflows.

Discover how to deploy cost-effective serverless ML inference endpoints using Amazon SageMaker. Learn about serverless architecture benefits and implementation strategies for production ML systems.

Personal journey and practical tips for data scientists pursuing AWS Cloud Practitioner certification. Learn effective study strategies and understand how cloud skills complement data science expertise.

Comprehensive guide to ensuring AI fairness and explainability using Amazon SageMaker Clarify. Learn how to detect bias, explain model predictions, and build responsible AI systems.

Learn how to leverage Amazon SageMaker Autopilot for automated machine learning. This guide covers building binary classification models with minimal code and maximum efficiency.

Master workflow orchestration with Apache Airflow on AWS. This practical guide walks through creating your first Directed Acyclic Graph (DAG) using Amazon Managed Workflows for Apache Airflow.

Learn how to deploy machine learning models serverlessly using AWS Lambda, Docker containers, and S3 storage. A cost-effective approach to ML model deployment in production.