|
Energy-Efficient Tensor Decomposition-Based Deep Neural Network Compression with High Accuracy
Figure: Procedure of the Compression Framework using ADMM for a TT-format DNN Model.
Invention Summary:
Deep Neural Networks (DNNs) are widely used in different computer vision tasks. Large-size DNN models cause high storage and computational demands and many DNN model compression methods, such as tensor decomposition are used to reduce...
Published: 10/28/2024
|
Inventor(s): Bo Yuan, Miao Yin
Keywords(s): Networks, Wireless
Category(s): Technology Classifications > Artificial Intelligence & Machine Learning, Technology Classifications > Software & Copyright, Technology Classifications > Software & Algorithms, Technology Classifications > Telecommunications & Networking, Technology Classifications > Physical Sciences & Engineering
|
