Face2Vec refers to the process of transforming faces to vectors, a process named vectorization that transforms objects/images/text into numerical representations (if you would like to learn more, read this). Recently, I added Face2Vec to the VectorHub repository (an open-source repository I maintain to host and share ___2Vec models). Face2Vec is…

For data scientists, ML Engineers, ML developers, search engine enthusiasts. Search engines and Top-K rankings are difficult to compare and are often difficult to justify. Top-K rankings are usually evaluated with several common criteria: Top results are more important than bottom-ranked results. A drop from 2nd to 3rd is more…

As SentencePiece is used in many cutting-edge NLP models, I decided to go into depth to explore what SentencePiece is about and understand a bit better about how and why it is used in NLP — (used in T5, Reformer, XLNet, Albert) and then their usage in the context of…

I write this in order to help data scientists work on problems they are passionate about in corporate and want to make their work more impactful than a simple 9–5. Personally — I think data science applications are bounded by creativity and knowledge of existing tools. Hence, this is a…

The following article is my summary of a popular machine learning system paper that I decided to analyse as it introduces a variety of concepts that try to capture a holistic understanding of the difficulty of building machine learning systems — especially scalable/different ones. These problems are only exacerbated in…

This is an unusual blog for me. Usually I write about about data science learnings, exploring new concepts I learn, understanding new research papers in a journey to become better at my craft. …

Before I explore what I have learnt, I think it is important to share what I think Kaggle is an accurate representation of and what it is not. Kaggle is a first and foremost a competition platform. While the domain is in data science — it simply offers problems in…