sdsds222/Simulated-Smooth-RNN
recurrent memory cell for sequence processing. Its core innovation provides flexible, high-resolution memory addressing at a constant O(1) cost. It achieves this with a controller that generates continuous floating-point addresses (e.g., 50.6), which are resolved by differentiable linear interpolation using only the two nearest slots.
Stars
—
Forks
—
Language
—
License
MIT
Category
Last pushed
Nov 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sdsds222/Simulated-Smooth-RNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
qdrant/quaterion
Blazing fast framework for fine-tuning similarity learning models
median-research-group/LibMTL
A PyTorch Library for Multi-Task Learning
zeiss-microscopy/OAD
Collection of tools and scripts useful to automate microscopy workflows in ZEN Blue using Python...
lucidrains/PoPE-pytorch
Efficient implementation (and explorations) into polar coordinate positional embedding (PoPE) -...
Zehong-Wang/Awesome-Weight-Space-Learning
A collection of weight space learning including papers, codes, and datasets.