Mudit Bachhawat

Tag: search

  • From Complete to Partial Feedback: Supervised Learning vs. Contextual Bandits

    Reading Time: 15 minutes

    At a high level, bandit algorithms and supervised learning models can look surprisingly similar. In both cases, the goal is to look at a given context and predict the best class or “arm” to choose. For a recommendation system, this might mean predicting which product a user is most likely to click on. But beneath…

  • Building Visual Search Engine

    Reading Time: < 1 minute

    Ever wonder how Google or Bing finds images similar to your image. The algorithms for generating text based 10 blue-links are very different from finding visually similar or related images. In this article, we will explain one such method to build a visual search engine. We will use the Caltech 101 dataset which contains images of common…