An overview of retrieval metrics (MRR, MAP, Precision, Recall) and techniques like RRF for building effective RAG systems.

Learn how to properly connect your Python virtual environments to Jupyter notebooks using kernels to avoid

Image classifier using fastai

A practical guide to BM25 and TF-IDF for text retrieval, explaining term frequency saturation and document length normalization.

Why accuracy isn't enough, and what metrics to use instead for classification problems.

A comprehensive guide to systematic error analysis for LLM systems using dimensional testing and qualitative coding methods

From linear regression's limitations to a working classifier — with memorable analogies and code.

A practical guide to deploying serverless ML inference endpoints on SageMaker, from setup to cleanup, with zero cost for testing.

From first principles to production: linear regression, gradient descent, bias-variance tradeoff, and L1/L2 regularization.

Debugging why I couldn't clone a repository I could see in my browser — the SSH key was linked to the wrong GitHub account.

Learn how to architect scalable RAG systems on AWS with Lambda concurrency, SQS queues, and scheduled provisioning.

Exploring how logistic regression works, from the math of log odds.

Learn how NDCG evaluates retrieval systems using graded relevance and position discounting.

Understanding the building blocks of deep learning through a complete linear regression implementation.

Learn transformer architecture through an intuitive networking party analogy — from embeddings to multi-head attention to full transformer blocks.

Understanding the fundamentals of approximate nearest neighbor search and reranking models for semantic search applications.

Learn how to implement serverless guardrails for LLM applications using AWS CDK, with input/output validation via Step Functions and Lambda.

Collaborative filtering system from scratch using fastai and PyTorch