• Image classification in the (real) Wild

    Image classification in the (real) Wild

    Last time we looked at how to best utilize a GPU when training Deep Learning models. Now it is time to put that to use and build a model that can tell apart the bewilderingly similar looking species of flora and fauna. This kind of image classification is generally called Fine grained visual categorization and…

  • Make the most of your GPU

    Make the most of your GPU

    The last couple of weeks, I have been playing around with data from my favorite app, iNaturalist. The good folks there, have released a dataset with 2.6M images of 10,000 species of assorted beasts and other flora. I’ve been trying to build a model that can separate the Jungle Babbler from the Yellow-Billed Babbler, a…

  • How Ads Work – Part 4, Auction

    How Ads Work – Part 4, Auction

    Welcome to the fourth post in the How Ads work series. Now it’s time to earn some money and sell ads ! This will be a short post and my goal in this post is to outline the basic mechanics of how the ads auction runs and complete our end to end understanding of the…

  • How Ads Work – Part 3, Ranking

    How Ads Work – Part 3, Ranking

    Welcome to  the third post in the How Ads work series. In this post we are going to discuss Ads Ranking in depth. This is where ML really comes to the party! At the end of Ads Retrieval, we have a pool of about a thousand fairly relevant ad candidates. Now it’s time to really…

  • How Ads Work – Part 2, Retrieval

    How Ads Work – Part 2, Retrieval

    In the last post we looked at an overview of the entire Ads system. In this post we will talk about Retrieval in depth. To recap, in Retrieval the goal is to cast a wide net over the entire Ads Index and quickly select a few thousand ad candidates which are broadly relevant for the…

  • How Ads Work – Part 1, Introduction

    How Ads Work – Part 1, Introduction

    Whether you’re searching for a new restaurant, scrolling through your social media or just getting laughs watching cat videos you have ads to thank for sponsoring this experience. When ads are good, you don’t notice them , when they are bad you get irritated and when they are unbelievably good you get creeped out.  In…