bo+yuan - Available Technologies | Rutgers University Innovation Ventures

Search Results - bo+yuan

2 Results Sort By:
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
Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding
Invention Summary: Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance. However, the state-of-the-art neural channel decoders cannot achieve high decoding performance and low complexity simultaneously. To overcome this challenge, Rutgers researcher have developed a novel doubly residual...
Published: 7/19/2023   |   Inventor(s): Bo Yuan, Chunhua Deng, Siyu Liao
Keywords(s): Electronics, Wireless
Category(s): Technology Classifications > Software & Algorithms, Technology Classifications > Software & Copyright, Technology Classifications > Physical Sciences & Engineering, Technology Classifications > Electronics/Semiconductor, Technology Classifications > Artificial Intelligence & Machine Learning, Technology Classifications > Telecommunications & Networking