A review of convolutional neural network architectures and their optimizations

S Cong, Y Zhou - Artificial Intelligence Review, 2023 - Springer
The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

Model compression and hardware acceleration for neural networks: A comprehensive survey

L Deng, G Li, S Han, L Shi, Y Xie - Proceedings of the IEEE, 2020 - ieeexplore.ieee.org
Domain-specific hardware is becoming a promising topic in the backdrop of improvement
slow down for general-purpose processors due to the foreseeable end of Moore's Law …

Rethinking bottleneck structure for efficient mobile network design

D Zhou, Q Hou, Y Chen, J Feng, S Yan - … 23–28, 2020, Proceedings, Part III …, 2020 - Springer
The inverted residual block is dominating architecture design for mobile networks recently. It
changes the classic residual bottleneck by introducing two design rules: learning inverted …

Tensor methods in computer vision and deep learning

Y Panagakis, J Kossaifi, GG Chrysos… - Proceedings of the …, 2021 - ieeexplore.ieee.org
Tensors, or multidimensional arrays, are data structures that can naturally represent visual
data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic …

A survey on green deep learning

J Xu, W Zhou, Z Fu, H Zhou, L Li - arXiv preprint arXiv:2111.05193, 2021 - arxiv.org
In recent years, larger and deeper models are springing up and continuously pushing state-
of-the-art (SOTA) results across various fields like natural language processing (NLP) and …

Automated detection of Parkinson's disease based on multiple types of sustained phonations using linear discriminant analysis and genetically optimized neural …

L Ali, C Zhu, Z Zhang, Y Liu - IEEE journal of translational …, 2019 - ieeexplore.ieee.org
Objective: Parkinson's disease (PD) is a serious neurodegenerative disorder. It is reported
that most of PD patients have voice impairments. But these voice impairments are not …

Early diagnosis of Parkinson's disease from multiple voice recordings by simultaneous sample and feature selection

L Ali, C Zhu, M Zhou, Y Liu - Expert Systems with Applications, 2019 - Elsevier
Parkinson's disease (PD) is a serious neurodegenerative disorder. It is reported that more
than 90% of PD patients have voice impairments. Multiple types of voice recordings have …

High-order tensor flow processing using integrated photonic circuits

S Xu, J Wang, S Yi, W Zou - Nature communications, 2022 - nature.com
Tensor analytics lays the mathematical basis for the prosperous promotion of multiway
signal processing. To increase computing throughput, mainstream processors transform …

Low rank tensor completion for multiway visual data

Z Long, Y Liu, L Chen, C Zhu - Signal processing, 2019 - Elsevier
Tensor completion recovers missing entries of multiway data. The missing of entries could
often be caused during the data acquisition and transformation. In this paper, we provide an …

Multiplex transformed tensor decomposition for multidimensional image recovery

L Feng, C Zhu, Z Long, J Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Low-rank tensor completion aims to recover the missing entries of multi-way data, which has
become popular and vital in many fields such as signal processing and computer vision. It …