automl/hierarchical_nas_construction
Official repository for "Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars" (NeurIPS 2023)
This project helps machine learning researchers design new, more efficient neural network architectures. It takes various neural architecture search (NAS) algorithms and datasets as input. The output is a highly optimized neural network architecture, along with performance metrics, ready for integration into larger deep learning models. It's intended for researchers and practitioners focused on advanced deep learning and AutoML.
No commits in the last 6 months.
Use this if you are a researcher aiming to explore and evaluate novel neural architecture search spaces and algorithms for deep learning models.
Not ideal if you are looking for a plug-and-play solution to immediately train and deploy a standard machine learning model, as this focuses on architectural research.
Stars
17
Forks
5
Language
Python
License
MIT
Category
Last pushed
Oct 26, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/automl/hierarchical_nas_construction"
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
IDEALLab/EngiBench
Benchmarks for automated engineering design
AI-team-UoA/pyJedAI
An open-source library that leverages Python’s data science ecosystem to build powerful...