Post-training Neural Network (NN) model compression is an attractive approach for deploying large, memory-consuming models on devices with limited memory resources. In this study, we investigate the rate-distortion tradeoff for NN model compression.
Articles
Related Articles
June 21, 2023
Facial Expression Re-targeting from a Single Character
Video retargeting for digital face animation is used in virtual reality, social media, gaming, movies, and...
Read More >
1 MIN READING
August 1, 2020
A system design for elastically scaling transaction processing engines in virtualized servers
Online Transaction Processing (OLTP) deployments are migrating from on-premise to cloud settings in order to exploit...
Read More >
1 MIN READING
July 2, 2018
Modified re-configurable quadrature balanced power amplifiers for half and full duplex RF front ends
An RF front-end (RFFE) architecture for dual-mode half and full duplex operation, employing a modified quadrature...
Read More >
1 MIN READING