All Articles

8 articles covering AI, machine learning, and more.

All Best Practices Deep Learning Machine Learning Basics Natural Language Processing Practical Guide RAG Engineering Tutorial

From Words to Intelligence: Building an MLP Classifier on Pretrained Sentence Embeddings

intermediateDeep Learning

A deep dive into pretrained sentence embeddings, MLP architecture, BatchNorm, Dropout, Adam, and early stopping — with full PyTorch implementation.

April 20, 202625 min read

#pytorch#nlp#deep-learning

Logistic Regression from Scratch in PyTorch: Every Line Explained

intermediateDeep Learning

Build a multi-class classifier in PyTorch without nn.Linear, without optim.SGD, without CrossEntropyLoss. Just tensors, autograd, and arithmetic — so you finally see what those helpers actually do.

April 19, 202615 min read

#pytorch#logistic-regression#autograd

ML Hyperparameters Explained for Beginners: Learning Rate, Epochs, Batch Size, L2, and Seed

beginnerMachine Learning Basics

A beginner-friendly explanation of core machine learning hyperparameters — learning rate, epochs, batch size, L2 regularization, and random seed — with simple examples and every important term explained clearly.

April 19, 20269 min read

#machine-learning#hyperparameters#learning-rate

TF-IDF + Logistic Regression: The Classical ML Baseline You Should Try First

intermediateMachine Learning Basics

Before reaching for LLMs or neural networks for text classification, try the boring thing. Here's how TF-IDF + Logistic Regression works, why it's often embarrassingly competitive, and where it breaks.

April 19, 202610 min read

#tf-idf#logistic-regression#sklearn

The Impartial Judge: Inside a Production ML Evaluation Harness

intermediateMachine Learning Basics

A developer's walkthrough of a real ML eval harness — F1, macro averaging, OOS recall, warmup, and p50/p95/p99 latency — and the design decisions behind each.

April 16, 202612 min read

#evaluation#metrics#f1-score

Semantic Caching & RAGAS Evaluation: Make Your RAG Pipeline Faster and Measurable

intermediateNatural Language Processing

Learn how to add semantic caching to your RAG pipeline for lower latency and cost, then measure quality with RAGAS evaluation metrics.

April 14, 202614 min read

#rag#semantic-caching#ragas

Chunking in RAG — Breaking Text the Right Way

intermediateRAG Engineering

Guide to text chunking strategies, why they matter, and how to pick the right one for your RAG project.

April 12, 202610 min read

#rag#chunking#embeddings

Understanding Transformers: The Architecture Behind Modern AI

intermediateDeep Learning

A comprehensive guide to understanding the Transformer architecture that powers GPT, BERT, and other modern language models.

April 12, 202612 min read

#transformers#deep-learning#nlp