Iterative clustering pruning for convolutional neural networks
J Chang, Y Lu, P Xue, Y Xu, Z Wei - Knowledge-Based Systems, 2023 - Elsevier
Convolutional neural networks (CNNs) have shown excellent performance in numerous
computer vision tasks. However, the high computational and memory demands in computer …
computer vision tasks. However, the high computational and memory demands in computer …
A zeroing neural dynamics based acceleration optimization approach for optimizers in deep neural networks
S Liao, S Li, J Liu, H Huang, X Xiao - Neural Networks, 2022 - Elsevier
The first-order optimizers in deep neural networks (DNN) are of pivotal essence for a
concrete loss function to reach the local minimum or global one on the loss surface within …
concrete loss function to reach the local minimum or global one on the loss surface within …
Leveraging filter correlations for deep model compression
We present a filter correlation based model compression approach for deep convolutional
neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise …
neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise …
Smart paddy field monitoring system using deep learning and IoT
Paddy is an essential nutrient worldwide. Rice gives 21% of worldwide human per capita
energy and 15% of per capita protein. Asia represented 60% of the worldwide populace …
energy and 15% of per capita protein. Asia represented 60% of the worldwide populace …
Global balanced iterative pruning for efficient convolutional neural networks
J Chang, Y Lu, P Xue, Y Xu, Z Wei - Neural Computing and Applications, 2022 - Springer
With the increase of structure complexity, convolutional neural networks (CNNs) take a fair
amount of computation cost. Meanwhile, existing research reveals the salient parameter …
amount of computation cost. Meanwhile, existing research reveals the salient parameter …
Pruning-and-distillation: One-stage joint compression framework for CNNs via clustering
Network pruning and knowledge distillation, as two effective network compression
techniques, have drawn extensive attention due to their success in reducing model …
techniques, have drawn extensive attention due to their success in reducing model …
Knowledge distillation methods for efficient unsupervised adaptation across multiple domains
Beyond the complexity of CNNs that require training on large annotated datasets, the
domain shift between design and operational data has limited the adoption of CNNs in many …
domain shift between design and operational data has limited the adoption of CNNs in many …
Senpis: Sequential network pruning by class-wise importance score
In the last decade, pattern recognition and decision making from images has mainly focused
on the development of deep learning architectures, with different types of networks such as …
on the development of deep learning architectures, with different types of networks such as …
Loss-aware automatic selection of structured pruning criteria for deep neural network acceleration
Structured pruning is a well-established technique for compressing neural networks, making
them suitable for deployment in resource-limited edge devices. This study presents an …
them suitable for deployment in resource-limited edge devices. This study presents an …
Automated picking-sorting system for assembling components in an IKEA chair based on the robotic vision system
With the rapid growth of the furniture product line industry and IKEA as the one of the
pioneers, manual labour (and its limits of stability and high cost) is increasingly being …
pioneers, manual labour (and its limits of stability and high cost) is increasingly being …