Recently there has been a lot of hype about google’s new language model. A direct competitor to OpenAI’s GPT-3. Not a lot of details about the model are available in the public domain but it has created huge waves not only in the industry but across newsrooms as well. The…

Since the advent of transformers, NLP gained a lot of traction, and a wide variety of tasks are already solved by GPT-3 and other big transformers-based models. But today we are going to take a step back and learn about word embeddings. In this blog, we are primarily going to…

Text to image generation models is the new fad in the market of AI. The latest model in this race is Google’s Imagen model. An answer to OPENAI’s DALLE-2 model. DALLE-2 made some great progress over DALLE-1 but in reality, it was not a successor of DALLE-1 but of GLIDE…

We all know that DALL-E 2 is one of the craziest models we have seen this year. DALL-E 2 is a text-to-image generation model developed by Open-AI researchers. It’s the second installment in the series of text-to-image generation models. DALL-E 2 is an extremely capable model with the ability to…

This is big, I mean really big. A few days ago Google announced that it has created a generalized AI, yes you heard it right, the generalized AI that can do everything. Google has claimed that it can perform around 600 tasks and this is the closest we have gotten…

The field of AI is evolving at a very rapid pace but rarely does something happen that shifts the paradigm. The last two big things in the field of AI are Generative Adversarial Networks and attention mechanisms. Both of these techniques or methods have been used in countless research papers…

Everyone in the field of AI and ML knows about KNN but if you will dig deeper than you will know that KNN is not a good algorithm for the big datasets. Training time for KNN is O(1) whereas testing time is O(nd*m) (n=training samples, d=dimension of data, m=test samples)…

Have you ever wondered, why we need teachers to learn things? Why can’t we learn everything on our own once we have learnt how to read, write and comprehend? The problem lies in what to learn and how much to learn. A teacher has many years of experience and thus…

It's been a while since the inception of U-Net, the network was initially designed to do medical image segmentation but since then it’s been used for all sorts of segmentation tasks. In my limited experience, I’ve always found that segmentation works better than object detection (given that you have the…