Pratik Sharma·Aug 29Building HeritageNet: An On-Device Image Classifier and Open Dataset for Nepali Heritage SitesA technical write-up of how I built a 26-class heritage-site classifier with transfer learning, added open-set rejection so it can say “I…A response icon1A response icon1
Pratik Sharma·Aug 28AI Can Recognize the Lumbini. It Had Never Seen My Neighborhood Temple.So I spent months teaching one to — and learned that the hardest part of building AI isn’t the AI.
Pratik Sharma·Jun 4What 1,338 Strangers Taught Me About Predicting Medical Bills with Linear RegressionA beginner-friendly walk through my first end-to-end machine learning project — from a confusing scatter plot to a live web app.
Pratik Sharma·May 31Sentiment Analysis with a Decision Tree: A Complete, Honest WalkthroughFrom raw Amazon reviews to a deployed Flask app — with every mistake, metric, and line of code explained
Pratik Sharma·May 26Building an Email Spam Detector with Naive Bayes: A Complete GuideComplete Guide to Naive Bayes: Text Classification and Spam Detection
Pratik Sharma·May 23I Analysed 12,964 Drug Overdose Deaths with Python — Here’s What the Data RevealedFrom messy CSV to statistical proof — a step-by-step Python analysis of fentanyl, demographics, and a decade of preventable deaths
Pratik Sharma·May 16You Are the Average of Your 5 Neighbors: Understanding KNN Through Olympic DataA Problem That Started My Machine Learning Journey
Pratik Sharma·May 12Why ‘Diesel’ Breaks Your Machine Learning Model — And How to Fix ItA complete blog on Ordinal Encoding, Label Encoding, and One-Hot Encoding with real Python code.
Pratik Sharma·May 8🌐 Principal Component Analysis (PCA): Simplifying High-Dimensional DataIntroduction
Pratik Sharma·Apr 18The Math We Forgot to Teach: Bridging the Gap Between Nepali Classrooms and the AI RevolutionA Personal RealizationA response icon1A response icon1