ML model monitoring

May 20, 2021 Kornel and I wrote about our team’s work on “Maintaining Machine Learning Model Accuracy Through Monitoring” on the DoorDash Engineering blog: Maintaining-Machine-Learning-Model-Accuracy-Through-Monitoring-_-DoorDash-Engineering-BlogDownload Jul 23, 2021 I presented at Fifth Elephant MLOps conference on behalf of the Machine Learning Platform team at DoorDash: 5el-mlops-model-monitoringDownload

My experience with Udacity Deep Learning Foundation course

If you don’t know what is machine learning, just know this from Francois Chollet (creator of Keras)’s “Deep Learning with Python” book : Classical programming vs. Machine learning After attending the AI Frontiers conference at the beginning of this year, I was amazed, fascinated and befuddled at what actually is machine learning and deep learning and all of the … Continue reading My experience with Udacity Deep Learning Foundation course

[Tech] Why is “Database Layer as a REST API” not common?

We have "database APIs" such as abstraction layers over multiple SQL databases and ORMs. But why not take it to the next step and make it a REST API like any other network call that we can make? Advantages would be: The sharing of database ORM models across multiple programming languages will be seamless. Making … Continue reading [Tech] Why is “Database Layer as a REST API” not common?

Micro targeting

Recently the Obama re-election campaign employed similar population-wide behavioral analytics to micro-target voters to ensure his re-election. There is no reason why we in India must not look to technology to devise ingenious methods for near real time data collection and population-wide analytics of social performance. This will not only help micro-target and localise welfare … Continue reading Micro targeting