lancopku/meSimp

Codes for "Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method"

26
/ 100
Experimental

This project helps machine learning engineers and researchers reduce the size and computational cost of their neural networks. By applying a "minimal effort" backpropagation method during training, it takes a standard neural network model and outputs a significantly smaller, yet equally or more accurate, version. This enables faster training and decoding in real-world applications.

No commits in the last 6 months.

Use this if you are training neural networks (like MLPs or LSTMs) and need to reduce their size and computational footprint without sacrificing accuracy, or even improving it.

Not ideal if you are not working with neural networks or if you are looking for a solution that does not involve modifying the training process itself.

deep-learning-optimization neural-network-compression model-simplification machine-learning-efficiency
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

18

Forks

3

Language

C#

License

Last pushed

May 13, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/lancopku/meSimp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.