Anirudh Acharya

Oct 25, 2022

Comparing Kantara and Avatar: The Last Airbender

I recently watched the movie Kantara( ಕಾಂತಾರ: ಒಂದು ದಂತಕಥೆ). It is an incredible and spectacular movie, I can’t remember the last time I walked out of a movie theater with such a sense of awe, being completely mesmerized. The movie is set in the forested lands of coastal Karnataka and…

Kannada

4 min read

Kannada

4 min read

Aug 19, 2022

Blogs vs. Podcasts

[This is a cross-post from one of my other blogs from Oct 2020] Over the last 10–15 years, I have been a very active consumer of online content, be it political op-eds, economics blogs, or computer science/technical blogs and newsletters. …

Blogging

2 min read

Blogging

2 min read

Jan 7, 2021

Learning and Pedagogy

Different people learn different things in different ways. Some people learn by listening to lectures and teachers, some by reading and self-study, and some by either doing or trying out things for themselves or in an apprenticeship sort of setting. Children mostly learn by either listening or doing things for…

Education

2 min read

Education

2 min read

Jan 7, 2021

Working Backwards

Amazon.com swears by “Working Backwards” as a tenet. And it is an excellent tenet that has worked well for the company. The work culture is such that even all of its employees adhere to it as a principle. Working at Amazon, I, too, got to learn the benefits of this…

Amazon

2 min read

Amazon

2 min read

Dec 26, 2020

AI Hype and the Opportunists

I recently watched this talk by Zachary Lipton. The talk is two years old but still relevant, important, and informative. Machine Learning: The Opportunity and the Opportunists - MIT Technology Review While artificial intelligence is delivering valuable solutions across many industries today, expectations are…events.technologyreview.com Here are a few things that stuck out for me on this matter - Excitement + Ignorance = Misinformation

Machine Learning

2 min read

Machine Learning

2 min read

Jun 4, 2020

Machine Learning Model DB as a Service

In many Machine Learning or Data Science workflows, it is common to save and checkpoint several models and compare how they perform on a held-out validation dataset. These saved models could be - checkpoints in a single training trial saved at different time epochs, in which case the network structure…

Machine Learning Tools

2 min read

Machine Learning Tools

2 min read

Published in The Startup

·Jun 11, 2019

Explainability in AI

In this post, I will share a few of my thoughts on explainability in AI/ML. Motivating Stories These situations ought to explain why explainability in AI is important. When a human is riding a self-driving taxi, and the taxi takes a sudden unexpected detour, you become suspicious and probably scared, wondering if…

Machine Learning

3 min read

Machine Learning

3 min read

Published in Apache MXNet

·May 29, 2018

MXNet 1.2 adds built-in support for ONNX

Authors: Anirudh Acharya, Rajan Singh , Roshani Nagmote, Hagay Lupesko — Amazon AI software engineers. MXNet 1.2 adds built-in support for ONNX With the latest Apache MXNet 1.2 release, MXNet users can now use a built-in API to import ONNX models into MXNet. …

Mxnet

4 min read

Mxnet

4 min read