Fastai

If you have heard about awesome AI course that fast.ai offers which is free of charge then you should definitely checkout. https://course.fast.ai/ is where you will find out all the details. Course takes a very hands on approach and anyone can write and bring up their ML model in under…

FastAI lesson 3 gives an overview of the basic concepts that are fundamental to deep learning. I learned quite a bit, so I’m writing all my thoughts and summaries in case this is helpful for anyone (or, more realistically, future me). Relu’s Rectified linear functions (aka, relu’s) are really simple linear…

Introduction We all might have used the classic MNIST dataset of containing 10 handwritten digits. Its often used as the introduction to image classification problem. Let’s try a different dataset for same problem of image classification. This time using Hindi Characters MNIST. It contains 36 categories for characters in Hindi language. …

FastAI lesson 2 notes and thoughts — I was honestly going to skip this lesson because it didn’t “technically” feature new AI concepts, but boy am I glad I didn’t! For starters, I can now enjoy my quokka vs capybara classification demo live, which isn’t something I expected to be able to do so quickly! Here’s a…

FastAI lesson 1 notes and thoughts — On the recommendation of some old colleagues, I’ve decided to work my way through fastai’s course to learn some deep learning basics. I like it! Very programmer-oriented, which is exactly what I need, given my personal technical background. …

Learn how the annotations for images are stored in the COCO annotation format (used by fastai) — The COCO (Common Objects in Context) format is a commonly used and popular data format for object detection and segmentation. It uses a JSON file to store annotations for each image in a dataset. In this article, I want to explain how the COCO format represents your data for annotation…

Introduction: Linear regression is a fundamental machine learning algorithm that is widely used in a variety of applications, such as finance, marketing, and engineering. It is a method for predicting a continuous output variable, based on one or more input variables, by finding a linear relationship between them. …

Build a sentiment analyzer using a pre-trained model — In my previous article on fastai, I discussed what fastai is, and how you can make use of pre-trained models and utilize transfer learning to train your own model using your own dataset. …

Since AI is here to stay, we might as well join in on the fun — MMA fighter Conor McGregor once exclaimed “We’re not here to take part, we are here to take over!” in his typical brash style. It could have easily been Artificial Intelligence saying the exact same phrase. The attention AI has garnered from the world grew considerably since OpenAI released its impressive…