Image by Cedric Yong from Pixabay

Explaining BERT Simply Using Sketches

BERT introduced by Google in 2018 was one of the most influential papers for NLP. But it is still hard to understand.

In my last series of posts on Transformers, I talked about how a transformer works and how to implement one yourself for a translation task.

--

--

--

4M Views. Bridging the gap between Data Science and Intuition. MLE@FB, Ex-WalmartLabs, Citi. Connect on Twitter @mlwhiz

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Does Anyone Know Any Website API for Finding the Category of a Domain? Check This Company

Arhaus Announces First Quarter 2022 Financial Results

Make your Machine Learning Models Come Alive with Streamlit

mountain with clouds

Identifying AR and MA terms using ACF and PACF Plots in Time Series Forecasting

How to Do a Data Science Project That Is Actually Useful

ABAC clauses: All good things take (too much) time

Automation is a ladder: part one

Weekly picks by Ali Alohali — مختارات اسبوعيه بواسطة علي العوهلي — Issue #14

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Rahul Agarwal

Rahul Agarwal

4M Views. Bridging the gap between Data Science and Intuition. MLE@FB, Ex-WalmartLabs, Citi. Connect on Twitter @mlwhiz

More from Medium

A guide to your first MLOps pipeline: Creating a regression model using MLFlow, Hydra and W&B

Installing and setting up Apache Mahout

How to save and re-use trained AI models. Python pickling hands-on in a nutshell

Dask: From Scratch to Scalable Analytics in Python! :)