How I trained a recommendation AI with 25M records in less than 5 minutes?
I’ve been following Jeremy Howard’s course on Practical Deep Learning With FastAI. Recently I learned about collaborative filtering, In the course we’ve trained a movie recommdner using the small version of the MovieLense dataset, in this post, we will train the 25 million version in just 5 minutes. The intractive Jupyter notebook version is here […]
Bulding a model from scratch: Predicting Diabetes
Last updated: 19 May 2025 · 14 min read Over the past few weeks, I’ve been working through the fantastic Practical Deep Learning course with FastAI, and after completing the Titanic dataset example in the course, I wanted to try the same principles on a custom data set—Pima Indians Diabetes.As we did in the course, […]
Building a FastAI H&M Text Classifier from Scratch (with Kaggle GPU)
Last updated: 26 Apr 2025 · 5 min read 1 · Dataset overview 2 · Notebook & environment setup 3 · Training a fashion‑aware language model 4 · Fine‑tuning the 322‑class classifier 5 · Reading the confusion matrix 6 · How to push accuracy higher Open notebook in kaggle 1. Dataset overview I used H&M scraped product data on Kaggle—9 677 product rows with rich metadata (ID, name, price, material, details text, […]