rdspring1/LSH_DeepLearning
Scalable and Sustainable Deep Learning via Randomized Hashing
This project helps deep learning engineers train and test neural networks more efficiently and sustainably. It takes your existing deep learning model and complex datasets, significantly reducing the computational load by focusing on the most important parts of the network. This means faster training times and lower energy consumption, making it ideal for those developing or deploying large AI models.
No commits in the last 6 months.
Use this if you are a deep learning engineer struggling with the high computational cost and energy demands of training and testing large neural networks on complex datasets.
Not ideal if you are working with small models or datasets where computational efficiency is not a primary concern, or if you need to maintain 100% of the original model's accuracy without any approximation.
Stars
94
Forks
22
Language
Java
License
Apache-2.0
Category
Last pushed
May 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rdspring1/LSH_DeepLearning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
optimatika/ojAlgo
oj! Algorithms
deepjavalibrary/djl-demo
Demo applications showcasing DJL
deeplearning4j/deeplearning4j
Suite of tools for deploying and training deep learning models using the JVM. Highlights include...
deepjavalibrary/djl
An Engine-Agnostic Deep Learning Framework in Java
deeplearning4j/deeplearning4j-examples
Deeplearning4j Examples (DL4J, DL4J Spark, DataVec)