Gemma 4

1 post connected to this tag.

Jul 22, 2026

Softmax vs Softplus: Competition, Positive Gates, and Backpropagation

Derive softmax and softplus, trace Laguna's learned gate projection through full attention and backpropagation, and compare where modern model families use softplus.

Read post →

Get my rants delivered to your inbox

I will send new posts as and when I write. No fixed cadence, just engineering notes, rants, and things I am thinking through.

Need an intelligent system to work on real hardware?

Embedded systems · Robotics · Constrained AI · CPU and HPC · Accelerators · Distributed systems

Work With Us / Antshiv Robotics

See engineering services

ShivasNotes

Independent notes on software, systems, AI workflows, robotics, and building Antsand in public.

Read

Latest articles
About
Projects
Resume

Support

Support this work
GitHub Sponsors
C-Kernel-Engine
Work With Us