meProp
Gradient optimization method
A technique to simplify backpropagation in neural networks by selectively computing only the most relevant gradients
meProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)
110 stars
12 watching
20 forks
Language: C#
last commit: over 4 years agoback-propagationcomputer-visiondeep-learningmepropnatural-language-processingnerual-network
Related projects:
| Repository | Description | Stars |
|---|---|---|
 mstksg/backprop | A Haskell library providing automatic heterogeneous back-propagation for differentiable programming and deep learning applications. | 180 |
 neuralmagic/sparseml | Enables the creation of smaller neural network models through efficient pruning and quantization techniques | 2,083 |
 cn-upb/deepcomp | A reinforcement learning-based system for optimizing multi-cell selection in wireless networks | 58 |
 ml-postech/gradient-inversion-generative-image-prior | An implementation of a method to invert gradients in federated learning to potentially reveal sensitive client data | 39 |
 xternalz/sdpoint | A deep learning method for optimizing convolutional neural networks by reducing computational cost while improving regularization and inference efficiency. | 18 |
 google-deepmind/optax | A gradient processing and optimization library designed to facilitate research and productivity in machine learning by providing building blocks for custom optimizers and gradient processing components. | 1,730 |
 deng-cy/deep_learning_topology_opt | Optimization code for topology optimization problems using machine learning and deep learning techniques | 107 |
 rentruewang/koila | A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution | 1,823 |
 saschagrunert/nn | A small neural network implementation of the backpropagation algorithm in Haskell | 127 |
 zou-group/textgrad | An autograd engine for textual gradients using large language models to backpropagate gradients. | 1,912 |
 intel/neural-compressor | Tools and techniques for optimizing large language models on various frameworks and hardware platforms. | 2,257 |
 delta2323/gb-gnn | Analyzes and optimizes the performance of graph neural networks using gradient boosting and various aggregation models. | 13 |
 pouyamghari/pof-mkl | An implementation of an online federated learning algorithm with multiple kernels for personalized machine learning | 0 |
 harshakokel/kigb | An open-source software framework that integrates human advice into gradient boosting decision trees for improved performance in machine learning tasks. | 8 |
 lanl-ansi/watermodels.jl | A Julia package for solving optimization problems in water distribution networks | 74 |