Published inTowards Data Science·PinnedMember-onlyWhat is MLOps — Everything You Must Know to Get StartedA complete walkthrough of ML systems development lifecycle and need for MLOps — Until recently, all of us were learning about software development lifecycle(SDLC) and how it goes from requirement elicitation → designing → development → testing → deployment → all the way down to maintenance. We were(and are) studying the waterfall model, iterative model, and agile models of software development. Now, we…Machine Learning10 min readMachine Learning10 min read
Oct 30, 2021Member-onlyWhat Google Recommends You do Before taking their ML or Data Science CourseFirst steps to learning data science & ML — foundations of DS & ML — Be it Andrew Ng’s ML/DL course on YouTube or any Data Science Bootcamp, you will need a certain degree of mathematical and statistical knowledge to not only understand but make a long-lasting, robust career as a data professional. This is a short and precise guide for all autodidact and beginners…Artificial Intelligence7 min readArtificial Intelligence7 min read
Published inTowards Data Science·Oct 18, 2021Member-onlyTraining BPE, WordPiece, and Unigram Tokenizers from Scratch using Hugging FaceComparing the tokens generated by SOTA tokenization algorithms using Hugging Face’s tokenizers package — Continuing the deep dive into the sea of NLP, this post is all about training tokenizers from scratch by leveraging Hugging Face’s tokenizers package. Tokenization is often regarded as a subfield of NLP but it has its own story of evolution and how it has reached its current stage where…Artificial Intelligence9 min readArtificial Intelligence9 min read
Published inTowards Data Science·Oct 5, 2021Member-onlyThe Evolution of Tokenization in NLP — Byte Pair Encoding in NLPIntroduction to different tokenization algorithms — NLP may have been a little late to the AI epiphany but it is doing wonders with organizations like Google, OpenAI releasing state-of-the-art(SOTA) language models like BERT and GPT-2/3 respectively. GitHub Copilot and OpenAI codex are among a few very popular applications that are in the news. As someone who…NLP11 min readNLP11 min read
Sep 23, 2021Member-onlyBuilding a Structured Financial Newsfeed using Python, SpaCy and StreamlitGetting started with NLP by building a Named Entity Recognition(NER) application — One of the very interesting and widely used applications of NLP is Named Entity Recognition(NER). Getting insights from raw and unstructured data is of vital importance. Uploading a document and getting the important bits of information from it is called information retrieval. Information retrieval has been a major task/challenge in…Data Science9 min readData Science9 min read
Sep 12, 2021Member-onlyBuilding at the Crossover of Research and Entrepreneurship — Optimizing my Work EthicFramework to produce valuable work. Relevant for anyone who doesn’t get well-defined or externally imposed goals. — Before you start working for an organisation, you are basically working in solitude. And the challenge with working solo is that there are no defined and externally imposed goals. You don’t have a laid-out path. This is a scenario I find myself in every other week or every other month…Data Science5 min readData Science5 min read
Sep 2, 2021Member-onlyHow Machine Learning leverages Linear Algebra to Solve Data ProblemsWhy you should learn the fundamentals of linear algebra — Machines or your computers only understand numbers and these numbers need to be represented and processed in a way that enables these machines to solve problems by learning from data instead of predefined instruction as in the case of programming. All types of programming use mathematics at some level and…Machine Learning7 min readMachine Learning7 min read
Published inTowards Data Science·Aug 20, 2021Member-onlyFirst Steps to Learning Data Science or ML after the RoadmapPre-requisites and pre-work before diving deep into data science and ML — At the start of this year, I published a mind map on the Data Science learning roadmap (shown below). The roadmap was widely accepted, that article got translated into different languages, and a large number of folks thanked me for publishing it. Everything was good until a few aspirants pointed…Data Science7 min readData Science7 min read
Published inTowards Data Science·Jun 18, 2021Member-onlyNew Machine Learning Specialisations for Advanced PractitionersWith a special focus on MLOps or ML Engineering — Today, you don’t need to go to a university or a college to pursue a career in machine learning or any data-driven domain but you need a plan and a roadmap to guide yourself. Once you have charted your own learning roadmap with a goal in mind, the next step…Machine Learning4 min readMachine Learning4 min read
Published inGeek Culture·May 15, 2021Member-onlyLearning to Build Robust ML Systems — Resources I Am Finding UsefulDocumentation, courses, and inspiration for your weekend. — I am going to keep this one short(but valuable🤞) without any detailed theme since I got my first jab of the vaccine today(Thursday, May 13) and my body isn’t allowing me to sit for long hours on my desk. So, here are a few things that have kept me occupied…Machine Learning3 min readMachine Learning3 min read
