Common Problems When Reproducing A Machine Learning Paper The Reproducibility JourneyWhen I first stepped into the field of machine learning, I spent quite a large amount of time on reading papers and trying to implement them. Of course,
MLOps Replacing "if" when writing a Bash Script Believe it or not, 95% of the time you do not need if statement. Most of the time you can always make do with some other alternatives to keep your
notes How to Read a Research Paper - 3-Pass Approach Note: This article is a summary of How to Read a Paper by S. Keshav. I wrote this as a reminder to myself on how to efficiently read a paper.
Machine Learning 3 Common Technical Debts in Machine Learning and How to Avoid Them Technical debt is the ongoing cost of expedient decisions made when implementing code. It is all the shortcuts or workarounds in technical decisions that give short-term benefit in earlier software
MLOps Deploying Ghost, MySQL, Let's Encrypt, Nginx Proxy using Docker Compose My search for the right blogging software wasn't all smooth sailing. It began with the usage suspects - Wordpress, Jekyll (and other markdown based - Hugo), Drupal, Joomla, etc. Eventually
Machine Learning The 1 Cycle Policy The 1cycle policy gives very fast results when training complex models. It follows the Cyclical Learning Rate (CLR) to obtain faster training time with regularization effect but with a slight modification.
Natural Language Processing An implementation guide to Word2Vec using NumPy and Google Sheets Word2Vec is touted as one of the biggest, most recent breakthrough in the field of Natural Language Processing (NLP). The concept is simple, elegant and (relatively) easy to grasp. A
