A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
A Lightweight Neural Network for Inferring ECG and Diagnosing Cardiovascular Diseases from PPG
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
A neural network is designed to jointly infer ECG and diagnose cardiovascular diseases (CVDs) from photoplethysmogram (PPG). ...
We analyze the latent connection between PPG and ECG as well as the CVDs-related features of PPG learned by the neural network, aiming at obtaining clinical insights from data. ...
After pruning the kernels at the first convolutional layer and the ECG generation layer of the full network, we replaced the cascaded FEMs and FTMs by the recursive ones and then fine-tuned the network ...
arXiv:2012.04949v2
fatcat:als777jgybhu5ik2tthh5ugep4
Binary Stochastic Filtering: feature selection and beyond
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Furthermore, the method is easily generalizable for neuron pruning and selection of regions of importance for spectral data. ...
Although such regularization is frequently used in neural networks to achieve sparsity of weights or unit activations, it is unclear how it can be employed in the feature selection problem. ...
Figure 2 : 2 Visualization of pruning with BSF. Neurons and BSF units are drawn in circles and squares respectively. Weights of BSF are shown as saturation of squares fill. ...
arXiv:2007.03920v1
fatcat:idq2dnefpjabvoa4jej2w3oiti
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. ...
The proposed technique gets rid of the additional retraining cycles by pruning the least important channels in a structured fashion at fixed intervals during the actual training phase. ...
Conclusion Convolutional Neural Networks are crucial for many computer vision tasks and require energy efficient implementation for low-resource settings. ...
arXiv:2002.09958v2
fatcat:msp267opdzbhzcwezphnwtlu4m
An Overview of Neural Network Compression
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Thus, in recent years there has been a resurgence in model compression techniques, particularly for deep convolutional neural networks and self-attention based networks such as the Transformer. ...
Hence, this paper provides a timely overview of both old and current compression techniques for deep neural networks, including pruning, quantization, tensor decomposition, knowledge distillation and combinations ...
The parameters induced by using VI-based least squares objective are sparse, improving the generalizability of the student network. ...
arXiv:2006.03669v2
fatcat:u2p6gvwhobh53hfjxawzclw7fq
Taxonomy of Saliency Metrics for Channel Pruning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We find that some of our constructed metrics can outperform the best existing state-of-the-art metrics for convolutional neural network channel pruning. ...
Pruning unimportant parameters can allow deep neural networks (DNNs) to reduce their heavy computation and memory requirements. ...
However, for convolutional neural networks, there is one level of pruning granularity -channel pruning -where there is a direct relationship between sub-blocks of the weight tensor and sub-blocks of the ...
arXiv:1906.04675v2
fatcat:lszdqa2fczfg7pcqch63oaypzi
BayesNAS: A Bayesian Approach for Neural Architecture Search
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Unlike other NAS methods, we train the over-parameterized network for only one epoch then update the architecture. ...
As a byproduct, our approach can be applied directly to compress convolutional neural networks by enforcing structural sparsity which achieves extremely sparse networks without accuracy deterioration. ...
The proposed Algorithm is generic for the weights in fully connected and convolutional neural networks. The training algorithm is iteratively indexed by t. Each iteration contains several epochs. ...
arXiv:1905.04919v2
fatcat:ni2qu2cujvbhrnid5wlyoajuvu
Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems. ...
In this paper, we propose a new layer-wise pruning method for deep neural networks. ...
Acknowledgements This work is supported by NTU Singapore Nanyang Assistant Professorship (NAP) grant M4081532.020, Singapore MOE AcRF Tier-2 grant MOE2016-T2-2-060, and Singapore MOE AcRF Tier-1 grant ...
arXiv:1705.07565v2
fatcat:gagmkieo5bbftgbxsdc2u7y27m
CirCNN
2017
Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture - MICRO-50 '17
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Large-scale deep neural networks (DNNs) are both compute and memory intensive. ...
Weight pruning achieves good compression ratios but suffers from three drawbacks: 1) the irregular network structure after pruning; 2) the increased training complexity; and 3) the lack of rigorous guarantee ...
waste for small-scale neural networks and additional chips for large-scale ones. ...
doi:10.1145/3123939.3124552
dblp:conf/micro/DingLWLLZWQBYMZ17
fatcat:yghqzgu65feuzjujvhvx2penie
Taxonomy of Saliency Metrics for Channel Pruning
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We find that some of our constructed metrics can outperform the best existing state-of-the-art metrics for convolutional neural network channel pruning. ...
Pruning unimportant parameters can allow deep neural networks (DNNs) to reduce their heavy computation and memory requirements. ...
However, for convolutional neural networks, there is one level of pruning granularity -channel pruning -where there is a direct relationship between sub-blocks of the weight tensor and sub-blocks of the ...
doi:10.1109/access.2021.3108545
fatcat:x6qbdcetujfg5jzdvpn4ivqy6e
Reducing Parameters of Neural Networks via Recursive Tensor Approximation
2022
Electronics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Large-scale neural networks have attracted much attention for surprising results in various cognitive tasks such as object detection and image classification. ...
This process factorizes a given network, yielding a deeper, less dense, and weight-shared network with good initial weights, which can be fine-tuned by gradient descent. ...
Acknowledgments: The authors also would like to thank the reviewers and editors for their reviews of this research.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/electronics11020214
fatcat:jgyhnb4punftbi5qcv4i3ndebu
AI in Game Playing: Sokoban Solver
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Games serve as a good breeding ground for trying and testing these algorithms in a sandbox with simpler constraints in comparison to real life. ...
In this project, we aim to develop an AI agent that can solve the classical Japanese game of Sokoban using various algorithms and heuristics and compare their performances through standard metrics. ...
a convolutional neural network. ...
arXiv:1807.00049v1
fatcat:iy7uno3kijhd7hkudasmyoi3xm
Efficient and Sparse Neural Networks by Pruning Weights in a Multiobjective Learning Approach
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Overparameterization and overfitting are common concerns when designing and training deep neural networks, that are often counteracted by pruning and regularization strategies. ...
Preliminary numerical results on exemplary convolutional neural networks confirm that large reductions in the complexity of neural networks with neglibile loss of accuracy are possible. ...
This work has been partially supported by EFRE (European fund for regional development) project EFRE-0400216. ...
arXiv:2008.13590v1
fatcat:6yaagh7adbhrdlsw53t67uajxu
Gradual Channel Pruning While Training Using Feature Relevance Scores for Convolutional Neural Networks
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The enormous inference cost of deep neural networks can be mitigated by network compression. Pruning connections is one of the predominant approaches used for network compression. ...
The proposed technique eliminates the need for additional retraining by pruning the least important channels in a structured manner at fixed intervals during the regular training phase. ...
CONCLUSION Convolutional Neural Networks are crucial for many computer vision tasks and require energy efficient implementation for low-resource settings. ...
doi:10.1109/access.2020.3024992
fatcat:xub7ht2agnhtxl7i6wtjjwzfwa
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. ...
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. ...
Acknowledgements We thank the AIM 2020 sponsors: HUAWEI, MediaTek, Google, NVIDIA, Qualcomm, and Computer Vision Lab (CVL) ETH Zurich.
A Teams and affiliations ...
arXiv:2009.06943v1
fatcat:2s7k5wsgsjgo5flnqaby26cn64
A Recursive Ensemble Learning Approach with Noisy Labels or Unlabeled Data
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Meanwhile, we provide guidelines for how to choose the most suitable among many candidate neural networks, with a pruning strategy that provides convenience. ...
INDEX TERMS Noisy labels, pruning strategy, semi-supervised learning, ensemble learning, deep learning, neural networks. ...
And Du et al. [18] also explored the question of ''how many samples are needed to learn a convolutional neural network?'' ...
doi:10.1109/access.2019.2904403
fatcat:43s3pigfbvcbvdqe7sg66szkny
« Previous
Showing results 1 — 15 out of 1,227 results