naotoo1/Beyond-Neural-Scaling
Implementation of Beyond Neural Scaling beating power laws for deep models and prototype-based models
This project helps machine learning engineers and researchers optimize deep learning models and prototype-based models. It takes your dataset and applies an optimal pruning algorithm to identify and remove less informative data, resulting in models that can achieve better performance with less data. The end result is more efficient models suitable for deployment on resource-constrained devices like mobile or edge devices.
Use this if you are a machine learning practitioner looking to improve the efficiency and scaling of your deep learning or prototype-based models, especially for mobile or edge deployments.
Not ideal if you are not working with deep learning or prototype-based models, or if your primary goal is not data optimization or model efficiency.
Stars
34
Forks
4
Language
Python
License
MIT
Category
Last pushed
Oct 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/naotoo1/Beyond-Neural-Scaling"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pykt-team/pykt-toolkit
pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models
microsoft/archai
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
google-research/morph-net
Fast & Simple Resource-Constrained Learning of Deep Network Structure
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...
IDEALLab/EngiBench
Benchmarks for automated engineering design