SMASH
Architecture search
An experimental method for efficiently searching neural network architectures using a single training run.
An experimental technique for efficiently exploring neural architectures.
489 stars
20 watching
57 forks
Language: Python
last commit: over 7 years ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 titu1994/neural-architecture-search | An implementation of Neural Architecture Search using Reinforcement Learning with a Controller RNN. | 432 |
| ajbrock/freezeout | A technique to accelerate neural network training by progressively freezing layers | 211 |
 negrinho/deep_architect | A modular framework for automatically searching over computational graphs to find good architectures for machine learning models | 121 |
 microsoft/archai | Automates the search for optimal neural network configurations in deep learning applications | 467 |
 neroloh/darts-tensorflow | This implementation provides a Tensorflow-based framework for searching different architectures in deep neural networks using 2nd-order approximations. | 73 |
 anjiecheng/mnasnet-pytorch | An implementation of a neural network architecture search algorithm optimized for mobile devices. | 271 |
 datacanvasio/hyperkeras | An AutoDL tool for optimizing neural networks and hyperparameters on TensorFlow and Keras | 30 |
 khanrc/pt.darts | An implementation of DARTS, a method for automatically designing neural network architectures. | 441 |
 0xprinc/huff_binarysearch | An implementation of binary search in Solidity for finding elements in sorted arrays. | 2 |
 linnanwang/alphax-nasbench101 | An implementation of a Neural Architecture Search agent using Monte Carlo Tree Search and a predictive model for efficient search of neural network architectures on the NASBench-101 dataset. | 167 |
 gomerudo/nas-env | An OpenAI Gym environment for searching neural network architectures | 29 |
 szagoruyko/binary-wide-resnet | An implementation of a 1-bit weight neural network architecture using PyTorch | 124 |
 seungwonpark/randwirenn | Implementation of neural network exploration with randomly wired architectures | 685 |
 jordanash/boostresnet | An implementation of a deep neural network architecture using boosting theory to improve its performance | 5 |
 jbarrow/lambdanet | An artificial neural network library for rapid prototyping and extension in Haskell. | 377 |