FreezeOut
by ajbrock
Accelerate Neural Net Training by Progressively Freezing Layers
AI summary
Layer freezeout
A technique to accelerate neural network training by progressively freezing layers
- stars
- 211
- forks
- 31
- watching
- 8
Similar projects
Found by comparing what the projects do, not just their names.
Architecture search
An experimental method for efficiently searching neural network architectures using a single training run.
Network tuner
Automates the search for optimal neural network configurations in deep learning applications
Neural net
An implementation of a multi-layer neural network in Python, allowing users to train and use the network for classification tasks.
Deep network designer
A DSL and toolkit for designing and optimizing deep neural networks in Haskell
Neural network optimizer
Trains artificial neural networks using the genetic algorithm
Layer-by-layer training method
An implementation of a novel neural network training method that builds and trains networks one layer at a time.
Deep learning toolkit
A Python framework for building deep learning models with optimized encoding layers and batch normalization.
Model optimizer
Enables the creation of smaller neural network models through efficient pruning and quantization techniques
Async neural network trainer
A distributed learning framework that enables peer-to-peer parameter averaging and asynchronous training of deep neural networks
Selective Stopping
Improves the performance of deep neural networks by selectively stopping training at different stages
Neural Network Library
An artificial neural network library for rapid prototyping and extension in Haskell.
Neural net trainer
A PyTorch framework simplifying neural network training with automated boilerplate code and callback utilities
Neural network builder
A deep learning framework on top of PyTorch for building neural networks.
Neural network
An implementation of a deep neural network architecture in PyTorch
Neural net booster
An implementation of a deep neural network architecture using boosting theory to improve its performance
