Educational app to illustrate inner workings of transformer models
-
Updated
Mar 18, 2026 - Go
Educational app to illustrate inner workings of transformer models
This project uses stochastic approximation algorithms to optimize investment strategies and queueing systems. Techniques include the Simultaneous Perturbation Stochastic Approximation (SPSA) for maximizing the Sharpe ratio and Stochastic Approximation (SA) for minimizing waiting times in a GI/GI/1 queue.
Add a description, image, and links to the spsa-algorithm topic page so that developers can more easily learn about it.
To associate your repository with the spsa-algorithm topic, visit your repo's landing page and select "manage topics."