Learning efficient convolutional networks through network slimming
The deployment of deep convolutional neural networks (CNNs) in many real world
applications is largely hindered by their high computational cost. In this paper, we propose a …
applications is largely hindered by their high computational cost. In this paper, we propose a …
Prediction of COVID-19 using genetic deep learning convolutional neural network (GDCNN)
RG Babukarthik, VAK Adiga, G Sambasivam… - Ieee …, 2020 - ieeexplore.ieee.org
Rapid spread of Coronavirus disease COVID-19 leads to severe pneumonia and it is
estimated to create a high impact on the healthcare system. An urgent need for early …
estimated to create a high impact on the healthcare system. An urgent need for early …
Autonomous deep learning: A genetic DCNN designer for image classification
Recent years have witnessed the breakthrough success of deep convolutional neural
networks (DCNNs) in image classification and other vision applications. DCNNs have …
networks (DCNNs) in image classification and other vision applications. DCNNs have …
Decore: Deep compression with reinforcement learning
Deep learning has become an increasingly popular and powerful methodology for modern
pattern recognition systems. However, many deep neural networks have millions or billions …
pattern recognition systems. However, many deep neural networks have millions or billions …
Layer pruning via fusible residual convolutional block for deep neural networks
P Xu, J Cao, F Shang, W Sun, P Li - arXiv preprint arXiv:2011.14356, 2020 - arxiv.org
In order to deploy deep convolutional neural networks (CNNs) on resource-limited devices,
many model pruning methods for filters and weights have been developed, while only a few …
many model pruning methods for filters and weights have been developed, while only a few …
Incremental training of deep convolutional neural networks
R Istrate, ACI Malossi, C Bekas… - arXiv preprint arXiv …, 2018 - arxiv.org
We propose an incremental training method that partitions the original network into sub-
networks, which are then gradually incorporated in the running network during the training …
networks, which are then gradually incorporated in the running network during the training …
Toward a period-specific optimized neural network for OCR error correction of historical Hebrew texts
O Suissa, M Zhitomirsky-Geffet… - ACM Journal on …, 2022 - dl.acm.org
Over the past few decades, large archives of paper-based historical documents, such as
books and newspapers, have been digitized using the Optical Character Recognition (OCR) …
books and newspapers, have been digitized using the Optical Character Recognition (OCR) …
Channel pruning guided by global channel relation
Y Cheng, X Wang, X Xie, W Li, S Peng - Applied Intelligence, 2022 - Springer
Channel pruning approaches have achieved some success in compressing deep
convolutional neural networks (CNNs). However, existing methods ignore the …
convolutional neural networks (CNNs). However, existing methods ignore the …
Improving robustness and efficiency of edge computing models
Existing designs of edge computing models are mostly targeted to improve the performance
of accuracy. Yet, besides accuracy, robustness and inference efficiency are also crucial …
of accuracy. Yet, besides accuracy, robustness and inference efficiency are also crucial …
Autonomously and simultaneously refining deep neural network parameters by a bi-generative adversarial network aided genetic algorithm
The choice of parameters, and the design of the network architecture are important factors
affecting the performance of deep neural networks. Genetic Algorithms (GA) have been used …
affecting the performance of deep neural networks. Genetic Algorithms (GA) have been used …