Anand K Subramanian



Hi,

This is Anand ( アナンド , if you prefer). I spend the majority of my time trying to understand the nuances of Deep Neural Networks, if not AI at large. I currently work at Bodygram , Tokyo as an Machine Learning Engineer. On a good day, I have at least a handful of failed ideas, or ideas that don't really work, which I realise while working out the math or while implementing.

I can passionately talk for hours on Karnatik Music (South-Indian Classical music), Philosophy of Art, and Science in general. Recently, I have picked up a passion for hiking and working my way up the 日本百名山 (100 Famous Mountains in Japan). I had previously worked on embedded systems and robotics before transitioning into Machine Learning.

Contact


Recent Posts

5 Feb 2024

Olafur Eliasson @ Azabudai Hills Gallery

A trip to Olafur Eliasson's exhibition at Azabudai Hills Gallery, Tokyo

#art #experience #photoessay #japan #தமிழ்

4 Aug 2023

Mathematics of Changing One's Mind

A guide to updating probabilistic beliefs using Jeffrey's rule and Pearl's method.

#math #ml #probability

4 Jul 2023

Scalene - A Python Profiler Case Study

A short note of ideas used in the high-performance python profiler - Scalene

#python #profiling #memory

29 Aug 2022

Improving the RANSAC Algorithm

Discussion about the MAGSAC algorithm, addressing a crucial hyperparameter selection issue for the RANSAC algorithm.

#math #ml #code #jax

29 Jun 2022

The Back-Gradient Trick

Stochastic Gradient Descent can be (kind of) reversed and can be used to compute gradients with respect to its hyperparameters.

#math #ml #gradient #graph #code #jax #deep-learning


© 2024 Anand K Subramanian License Design Built with Franklin.jl