research-article

Public Access

An Efficient Video Prediction Recurrent Network using Focal Loss and Decomposed Tensor Train for Imbalance Dataset

Authors:

Mousam Hossain,

Ronald F. DeMara,

Yu BaiAuthors Info & Claims

GLSVLSI '21: Proceedings of the 2021 Great Lakes Symposium on VLSI

Pages 391 - 396

https://doi.org/10.1145/3453688.3461748

Published: 22 June 2021 Publication History

Abstract

Nowadays, from companies to academics, researchers across the world are interested in developing recurrent neural networks due to their incredible feats in various applications, such as speech recognition, video detection, predictions, and machine translation. However, the advantages of recurrent neural networks accompanied by high computational and power demands, which are a major design constraint for electronic devices with limited resources used in such network implementations. Optimizing the recurrent neural networks, such as model compression, is crucial to ensure the broad deployment of recurrent neural networks and promote recurrent neural networks for implementing most resource-constrained scenarios. Among many techniques, tensor train (TT) decomposition is considered an up-and-coming technology. Although our previous efforts have achieved 1) expanding limits of many multiplications within eliminating all redundant computations; and 2) decomposing into multi-stage processing to reduce memory traffic, this work still faces some limitations. In particular, current TT decomposition on recurrent neural networks leads to a complex computation sensitive to the quality of training datasets. In this paper, we investigate a new method for TT decomposition on recurrent neural networks for constructing an efficient model within imbalance datasets to overcome this issue. Experimental results show that the proposed new training method can achieve significant improvements in accuracy, precision, recall, F1-score, False Negative Rate (FNR), and False Omission Rate (FOR).

Supplemental Material

MP4 File

Presentation video for the paper titled 'An Efficient Video Prediction Recurrent Network using Focal Loss and Decomposed Tensor Train for Imbalance Dataset'

Download
212.15 MB

References

[1]

Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).

[2]

Y. Bai, D. Fan, and M. Lin. 2018. Stochastic-Based Synapse and Soft-Limiting Neuron with Spintronic Devices for Low Power and Robust Artificial Neural Networks. IEEE Transactions on Multi-Scale Computing Systems 4, 3 (2018), 463--476. https://doi.org/10.1109/TMSCS.2017.2787109

[3]

Yuxuan Cai, Hongjia Li, Geng Yuan, Wei Niu, Yanyu Li, Xulong Tang, Bin Ren, and Yanzhi Wang. 2020. YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design. arXiv preprint arXiv:2009.05697 (2020).

[4]

Kyunghyun Cho, Bart Van Merriënboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014).

[5]

Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yipeng Zhang, Jian Tang, Qinru Qiu, Xue Lin, and Bo Yuan. 2017. CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices. In Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture (Cambridge, Massachusetts) (MICRO-50 '17). Association for Computing Machinery, New York, NY, USA, 395--408. https://doi.org/10.1145/3123939.3124552

Digital Library

[6]

Timur Garipov, Dmitry Podoprikhin, Alexander Novikov, and Dmitry Vetrov. 2016. Ultimate tensorization: compressing convolutional and fc layers alike. arXiv preprint arXiv:1611.03214 (2016).

[7]

Tian Guo, Tao Lin, and Nino Antulov-Fantulin. 2019. Exploring interpretable LSTM neural networks over multi-variable data. In International Conference on Machine Learning. PMLR, 2494--2504.

[8]

Tian Guo, Zhao Xu, Xin Yao, Haifeng Chen, Karl Aberer, and Koichi Funaya. 2016. Robust online time series prediction with recurrent neural networks. In 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA). Ieee, 816--825.

[9]

Yanhui Guo, Siming Han, Chuanhe Shen, Ying Li, Xijie Yin, and Yu Bai. 2018. An Adaptive SVR for High-Frequency Stock Price Forecasting. IEEE Access 6 (2018), 11397--11404. https://doi.org/10.1109/ACCESS.2018.2806180

[10]

Yiwen Guo, Anbang Yao, and Yurong Chen. 2016. Dynamic network surgery for efficient dnns. arXiv preprint arXiv:1608.04493 (2016).

[11]

Zhen He, Shaobing Gao, Liang Xiao, Daxue Liu, Hangen He, and David Barber. 2017. Wider and deeper, cheaper and faster: Tensorized lstms for sequence learning. arXiv preprint arXiv:1711.01577 (2017).

[12]

Nan Rosemary Ke, Konrad Żoĺna, Alessandro Sordoni, Zhouhan Lin, Adam Trischler, Yoshua Bengio, Joelle Pineau, Laurent Charlin, and Christopher Pal. 2018. Focused hierarchical rnns for conditional sequence processing. In International Conference on Machine Learning. PMLR, 2554--2563.

[13]

Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980--2988.

[14]

Zachary C Lipton, David C Kale, Charles Elkan, and Randall Wetzel. 2015. Learning to diagnose with LSTM recurrent neural networks. arXiv preprint arXiv:1511.03677 (2015).

[15]

Jingen Liu, Jiebo Luo, and Mubarak Shah. 2009. Recognizing realistic actions from videos "in the wild". In 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1996--2003.

[16]

Xindian Ma, Peng Zhang, Shuai Zhang, Nan Duan, Yuexian Hou, Dawei Song, and Ming Zhou. 2019. A tensorized transformer for language modeling. arXiv preprint arXiv:1906.09777 (2019).

[17]

Chuhan Min, Aosen Wang, Yiran Chen, Wenyao Xu, and Xin Chen. 2018. 2pf-pce: Two-phase filter pruning based on conditional entropy. arXiv preprint arXiv:1809.02220 (2018).

[18]

Alexander Novikov, Dmitry Podoprikhin, Anton Osokin, and Dmitry Vetrov. 2015. Tensorizing neural networks. arXiv preprint arXiv:1509.06569 (2015).

[19]

Yu Pan et al. 2019. Compressing recurrent neural networks with tensor ring for action recognition. In AAAI, Vol. 33. 4683--4690.

Digital Library

[20]

Hasim Sak, Andrew W Senior, and Françoise Beaufays. 2014. Long short-term memory recurrent neural network architectures for large scale acoustic modeling. (2014).

[21]

A. Samiee, P. Borulkar, R. F. DeMara, P. Zhao, and Y. Bai. 2019. Low-Energy Acceleration of Binarized Convolutional Neural Networks using a Spin Hall Effect based Logic-in-Memory Architecture. IEEE Transactions on Emerging Topics in Computing (2019), 1--1. https://doi.org/10.1109/TETC.2019.2915589

[22]

Ashkan Samiee, Yinjie Huang, and Yu Bai. 2018. FRLDM: Empowering K-nearest Neighbor (KNN) through FPGA-based Reduced-rank Local Distance Metric. In 2018 IEEE International Conference on Big Data (Big Data). 4742--4746. https: //doi.org/10.1109/BigData.2018.8622087

[23]

Jürgen Schmidhuber and Sepp Hochreiter. 1997. Long short-term memory. Neural Comput 9, 8 (1997), 1735--1780.

Digital Library

[24]

Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. arXiv preprint arXiv:1409.3215 (2014).

[25]

Andros Tjandra, Sakriani Sakti, and Satoshi Nakamura. 2017. Compressing recurrent neural network with tensor train. In 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 4451--4458.

[26]

Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2016. Learning structured sparsity in deep neural networks. arXiv preprint arXiv:1608.03665 (2016).

[27]

Yinchong Yang et al. 2017. Tensor-train recurrent neural networks for video classification. In ICML. 3891--3900.

[28]

Jinmian Ye et al. 2018. Learning compact recurrent neural networks with block-term tensor decomposition. In CVPR. 9378--9387.

[29]

Miao Yin, Siyu Liao, Xiao-Yang Liu, Xiaodong Wang, and Bo Yuan. 2020. Compressing recurrent neural networks using hierarchical tucker tensor decomposition. arXiv preprint arXiv:2005.04366 (20

Cited By

Ma XTang JBai Y(2023)Locality-sensing Fast Neural Network (LFNN): An Efficient Neural Network Acceleration Framework via Locality Sensing for Real-time Videos Queries2023 24th International Symposium on Quality Electronic Design (ISQED)10.1109/ISQED57927.2023.10129395(1-8)Online publication date: 5-Apr-2023
https://doi.org/10.1109/ISQED57927.2023.10129395
Liu MLuo SHan KDeMara RBai Y(2022)Autonomous Binarized Focal Loss Enhanced Model Compression Design Using Tensor Train DecompositionMicromachines10.3390/mi1310173813:10(1738)Online publication date: 14-Oct-2022
https://doi.org/10.3390/mi13101738

Index Terms

An Efficient Video Prediction Recurrent Network using Focal Loss and Decomposed Tensor Train for Imbalance Dataset
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision tasks
        Activity recognition and understanding

Recommendations

Prediction of Sunspot Series Using a Recurrent Neural Network
ICISA '11: Proceedings of the 2011 International Conference on Information Science and Applications

A prediction scheme for sunspot series using a Recurrent Neural Network is proposed in this paper. The recurrent neural network adopted in this scheme is the Bilinear recurrent neural network (BRNN). Since the BRNN is based on the bilinear polynomial, ...
Sunspot series prediction using a Multiscale Recurrent Neural Network
ISSPIT '10: Proceedings of the The 10th IEEE International Symposium on Signal Processing and Information Technology

A prediction scheme for sunspot series using a Multiscale Bilinear Recurrent Neural Network (M-BRNN) is proposed in this paper. The recurrent neural network adopted in this scheme is the Bilinear recurrent neural network. The M-BRNN is a combination of ...
Sunspot series prediction using adaptively trained Multiscale-Bilinear Recurrent Neural Network
AICCSA '11: Proceedings of the 2011 9th IEEE/ACS International Conference on Computer Systems and Applications

A prediction scheme for sunspot series using a Recurrent Neural Network is proposed in this paper. The recurrent neural network adopted in this scheme is the Multiscale-Bilinear Recurrent Neural Network with an adaptive learning algorithm (M-BRNN (AL)). ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

GLSVLSI '21: Proceedings of the 2021 Great Lakes Symposium on VLSI

June 2021

504 pages

ISBN:9781450383936

DOI:10.1145/3453688

General Chairs:
Yiran Chen
Duke University, USA
,
Victor Zhirnov
Semiconductor Research Corporation, USA
,
Program Chairs:
Avesta Sasan
George Mason University, USA
,
Ioannis Savidis
Drexel University, USA

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGDA: ACM Special Interest Group on Design Automation

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 June 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Data Availability

Presentation video for the paper titled 'An Efficient Video Prediction Recurrent Network using Focal Loss and Decomposed Tensor Train for Imbalance Dataset' https://dl.acm.org/doi/10.1145/3453688.3461748#GLSVLSI21-vlsi33s.mp4

Funding Sources

Conference

GLSVLSI '21

Sponsor:

SIGDA

GLSVLSI '21: Great Lakes Symposium on VLSI 2021

June 22 - 25, 2021

Virtual Event, USA

Acceptance Rates

Overall Acceptance Rate 312 of 1,156 submissions, 27%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
317
Total Downloads

Downloads (Last 12 months)94
Downloads (Last 6 weeks)21

Reflects downloads up to 22 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Ma XTang JBai Y(2023)Locality-sensing Fast Neural Network (LFNN): An Efficient Neural Network Acceleration Framework via Locality Sensing for Real-time Videos Queries2023 24th International Symposium on Quality Electronic Design (ISQED)10.1109/ISQED57927.2023.10129395(1-8)Online publication date: 5-Apr-2023
https://doi.org/10.1109/ISQED57927.2023.10129395
Liu MLuo SHan KDeMara RBai Y(2022)Autonomous Binarized Focal Loss Enhanced Model Compression Design Using Tensor Train DecompositionMicromachines10.3390/mi1310173813:10(1738)Online publication date: 14-Oct-2022
https://doi.org/10.3390/mi13101738

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents