lancopku/meProp
meProp: Sparsified Back Propagation for Accelerated Deep Learning (ICML 2017)
This project helps machine learning practitioners train deep neural networks significantly faster while improving model accuracy. It takes your existing neural network setup for tasks like natural language processing or image classification, and by intelligently updating only the most important parts of the network during training, it produces a more accurate and quickly-trained model. This is for machine learning engineers or researchers who build and train deep learning models.
110 stars. No commits in the last 6 months.
Use this if you need to accelerate the training of deep learning models for tasks such as dependency parsing, POS tagging, or image classification, and you want to achieve better accuracy than standard training methods.
Not ideal if your primary goal is extreme memory optimization or if you are not working with deep neural networks.
Stars
110
Forks
20
Language
C#
License
—
Category
Last pushed
Mar 29, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lancopku/meProp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform