In this post we will cover high level concepts of using Transformers in Vision (ViT) tasks. We will follow the contours of ICLR 2021 paper by Google Brain — “An Image is Worth 16x16 Words Transformers for Image Recognition at Scale”. First we will cover the concept of ViT at a high level. Then we will do a quick recap of Transformers in general. And finally we will look at some implementation level details of Vision Transformers (ViT).
This post is divided into three parts:
NLP (Natural Language Processing) has popularised the use of…
In this blog I will introduce the field of Reinforcement Learning(RL), how and when this form of Machine Learning is used. I will also talk about the path you should follow to build expertise in the field of RL.
Reinforcement Learning (RL) is a sub topic under Machine Learning. It is one of the fastest growing disciplines helping make AI real. Combining Deep Learning with Reinforcement Learning has led to many significant advances that are increasingly getting machines closer to act the way humans do. All intelligent beings start with a small knowledge. …
Apart from overseeing successful ventures and providing growth mentoring to startups, I like to explore and write about latest advances in AI and Deep Learning.