Srikanth Cherla

I came across git worktrees by accident last week.

A walkthrough of the SAME autoencoder’s bottleneck — five operations that shape a latent space for downstream diffusion, and the design reasoning that may have led the authors away from the VAE.

Six steps to get a self-hosted image generation service into production on Cloud Run GPU — what I landed on at each step, how I got there, and what each one still costs.

A walkthrough of the SAME autoencoder architecture — how patching and a Transformer Resampling Block achieve 4096× temporal compression of stereo audio without a single strided convolution.

I first used Vim around 2003-04, when it was pushed onto us during an undergraduate computer science course — it was either that or Emacs if you were serious about writing code.

This website has been running on WordPress since I first set it up in 2013 — hosted on a shared cPanel server at Arvixe (and then Domain Racer).

Just the Same opens Free Hand (1975), my favourite among all of Gentle Giant’s brilliant albums.

Corpse Pose is from Leaves Turn Inside You (2001), the final record Unwound made before disbanding.

Revolve is from Houdini (1993), one of the Melvins’ most accessible albums.

The opening track from Songs for the Deaf (2002), one of QOTSA’s finest records.

I recently completed a Coursera foundation course on Large Language Models — my first structured learning in a while.

I’ve been building Unity’s AI assistant — Muse — since April 2023, and it recently got a moment in the spotlight: Microsoft featured it at their Build conference as a customer success story.

Tool is one of my favourite bands, and Invincible is a piece I’d been wanting to cover for a while.

I returned from paternity leave to find the team had shifted from Unity’s C# codebase to TypeScript.

I’d been at Unity for over a year without ever properly learning C#.

An original acoustic arrangement of Man in the Box by Alice in Chains — released as a tribute on the 30th anniversary of their debut album Facelift.

Reinforcement Learning is one of the most interesting topics in computer science and ML.

My favourite track from the Road Rash video game soundtrack — see the Outshined post for how I came across both songs.

My connection to this song goes back to before I even knew what Soundgarden or grunge music were.

Despite Soundgarden being one of my favourite bands from the 1990s grunge era, I’d never learned to play any of their songs.

A cover of Americana by the Offspring — not one of the album’s most popular tracks, but one of the most fun and energetic ones to play.

After joining Unity I needed to get up to speed on game design.

I’m very pleased to announce that, starting today, I will be a Senior Machine Learning Developer at Unity Labs in Copenhagen.

Third in my series of Primus covers.

Today I handed in my resignation at Moodagent.

Second in my planned series of five Primus covers.

I’ve long admired Larry Lalonde’s distinctive guitar work alongside Les Claypool’s intricate bass playing.

Completed the second of three parts of Dan Grossman’s Programming Languages course from the University of Washington on Coursera.

Perpetual Black Second is from Nothing (2002), recorded during the first weeks of pandemic lockdown.

I wasn’t immediately taken with this song but reconnected with it while preparing for Tool’s Fear Inoculum release, and got drawn in enough to learn it properly.

Completed the first part of Dan Grossman’s Programming Languages specialisation from the University of Washington on Coursera, scoring 98%.

Four of us from Moodagent — Reinier de Valk, Pierre Lafitte, Tomas Gajarsky, and myself — are attending ISMIR 2019 in Delft, Netherlands.

Hangar 18 from Rust in Peace (1990) is essentially a vehicle for one of thrash metal’s great dual-guitar solo sections.

Two years after passing Grade 6 with distinction, I spent about a year preparing for Grade 7.

It’s been about four months since I wrote here about leaving Jukedeck.

I resisted pandas for a long time, then found myself spending way too much time writing data processing routines from scratch on a recommender systems project.

I’ve been volunteering with peers in India to promote awareness of music technology through the Music Tech Community – India initiative.

After leaving Jukedeck I completed the four-course Recommender Systems specialisation from the University of Minnesota on Coursera: Introduction to Recommender Systems: Non-personalised and Content-based Nearest Neighbour Collaborative Filtering Recommend…

This is just a quick post to let everyone know that I have decided to leave Jukedeck.

I was invited by Music Tech Community – India to speak at an event in Bengaluru on December 29th, focused on “Machine Learning for Art & Music Generation.”

I attended ISMIR 2018 in Paris with colleagues from Jukedeck to present our StructureNet paper.

The Rush cover I hinted at after Jacob’s Ladder.

A paper I co-authored with colleagues from Jukedeck has been accepted at ISMIR 2018 in Paris.

I recently ran into a situation where I had to initially train a neural network first on one dataset, save it and then load it up later to train it on a different dataset (or using a different training procedure).

Completed UCSD’s Machine Learning with Big Data on Coursera with a 98.9% mark.

Completed UCSD’s Big Data Integration and Processing on Coursera with 97.7%.

This track was what got me into Alice in Chains.

When TensorFlow 1.4 was released there were very few fully working examples of the Datasets API for sequence data.

I learned this piece while recovering from a bicycle accident.