FUKUCHI Tomohide の履歴(No.117)

Scaling Deep-Learning Inference

(with Reconfigurable FPGA-Cluster-based Architecture)

Background and Motivation†

Research Goal†

The goal of this thesis is to propose a DNN (CNN) parallelization algorithm, architecture, and design of a Real-time AI-Enabled Real-time Bio-system.

↑

Research Schedule†

Date	Task
☑Nov 1 ~ Dec 7, 2020	Resize MNIST dataset
Dec 21 ~ TBD	Update paper "Hand Gesture Processing with Sensor Fusion based on Neuromorphic System"
☑Dec 24 ~ Jan 8, 2021	EMG dataset collection using Myo
☑Jan 9 ~ 20, 2021	Implementing signal processing part in Matlab
☑Jan 20 ~ Feb 28, 2021	Add source code and dataset into github
☑Jan 17 ~ 31, 2021	Help to revise ETLTC20210 papers
☑Feb 20 ~ 26, 2021	Test 3D printer
☑Mar 2 ~ Mar 5, 2021	Study AIRBiS project and write slide
☑Mar 2 ~ Mar 12, 2021	Inference of batch test on FPGA and communicate network with UI for 64x64 grayscale
☑Mar 12 ~ Mar 22, 2021	Inference of batch test on FPGA and communicate network with UI for 128x128 grayscale
☑Mar 15 ~ Mar 23, 2021	Write Hardware Acceleration Part of journal draft
☑Mar 24, 2021	Find source code in internet for parallel CNN
☑Mar 26 ~ Apr 2, 2021	comparison to other works
☑Apr 3 ~ Apr 14, 2021	work on training on FPGA for AIRBiS project
☑Apr 15 ~ Apr 28, 2021	Work on speed up for time cost using SDSoC
☑Apr 29 ~ May 16	Modify speed up sample code for AIRBiS CNN
☑May 17 ~ June 25	Design new CNN mapping algorithm
☑June 21 ~ August 2	Prepare and improve the paper for hardware part
☑June 26~ July 7	Evaluate CNN mapping algorithm
☑July 17 ~ August 29	Prepare a paper for other publication opportunity
☑July 17 ~ July 30	Optimize convolution acceleration to more speed up
☑Aug 12 ~ Aug 31	Improving paper, experiment of pragma for the inference
☑Sept 1 ~ Sept 30	Test and find the example code of multithread on FPGA, writing Abstract for ETLTC2022
☑Oct 1~ Dec 3	Multithread on FPGA
☑Oct 30~ Nov 5	Making a slide for the Progress Report Presentation
☑Oct 26 ~ Nov 19	Reading a paper "Federated Learning with Spiking Neural Networks"
☑Nov 19 ~ Nov 22	Understand and run the AIRBiS FL
☑Nov 23 ~ Dec 3	Convert the AIRBiS CNN to SNN
☑Dec 4 ~ Dec 18	Experiment and Evaluation of SNN in SW
☑Dec 19 ~ Dec 22	Setup of FPGA for SNN in HW
☑Dec 23 ~ Dec 30	Experiment and Evaluation of SNN in HW
☑Jan 4, 2022	Take a Mark's guidance on 5:30, new road map
☑Jan 5 ~ Jan 13 , 2022	AIRBiS CNN to SNN Conversion in MATLAB
☑Jan 11, 2022	Making presentation for the AIRBiS CNN to SNN conversion result on 5PM
☑Jan 15 ~ Jan 22, 2022	Understanding communication between multiple SNPCs without router
☑Jan 23 ~ Jan 31, 2022	Understanding communication between multiple SNPCs with router
☑Feb 1 ~ Feb 11, 2022	SNPC tutorial
☑Feb 11~ Feb 14, 2022	Accuracy in SNPC for MNIST classification, comparison with ANN for the complexity
Mar 15, 2022	Making presentation for the result of the comparison of ANN and SNPC at Professor's office on 5PM
☑Feb 15 ~ Feb 20, 2022	Simulating of the STDP learning algorithm for the NASH in BinsNet
☑Feb 20 ~ Mar 3, 2022	Simulating of the STDP learning algorithm for the NASH in RTL
☑Feb 3 ~ Mar 10, 2022	Evaluating the NASH for x-ray image classification
☑Mar 9 ~ Mar 12	Update Introduction, Related Works part
☑Mar 13 ~ Mar 16	Update Motivation, System Architecture part
☑Mar 17 ~ Mar 24	Update evaluation part
☑Mar 18, 17:00	Meeting with professor about the progress of the paper draft
☑Feb 8 ~ Mar 20, 2022	Explore the Poisson and single spike coding scheme for the AIRBiS SNN optimization
☑Mar 15 ~ Mar 21, 2022	Mapping AIRBiS SNN on NASH by adapting genetic algorithm
☑Mar 11 ~ Mar 20, 2022	Update the results in the IEEE Access paper
Mar, 21 2022	Present the complete IEEE Access paper
☑April 21 ~ April 26	Developing SNN in SW for the pneumonia detection
☑April 27 ~ May 2	Evaluation of SNN in SW
May 3 ~ May 28	Developing SNN in HW for the pneumonia detection
April 30 ~ May 30	Journal paper draft update
May 25 ~ May 30	Evaluation of accuracy, and power consumption of Federated Learning with SNN in Chest X-ray data
May 25 ~ Jun 3	Quantization of the SNN trained parameter in pytorch
May 31 ~ Jun 6	Modify the architecture of NASH to AIRBIS CNN architecture
Jun 7 ~ Jun 15	Evaluation of accuracy, power consumption, hardware complexity

Schedule last updated on: 5/25/2022

↑

Achievements†

↑

Conference Papers†

"Efficient AI-Enabled Pneumonia Detection in Chest X-ray Images based on a Neuromorphic Spiking Neural Network," 14th International Conference on Computational Collective Intelligence,
- Submitted Version (5/9/2022), (latex, pdf)

"AIRBIS-2:Efficient AI-Enabled Pneumonia Detection in Chest X-ray Images based on a Neuromorphic Spiking Neural Network," 14th Asian Conference on Intelligent Information and Database Systems,
- Submitted Version (5/25/2022), (latex, pdf)

↑

Bibliography†

↑

Biomedical Apprication in ANN†

2022 Abdulkareem, M., Petersen, S.E.: The promise of ai in detection, diag nosis, and epidemiology for combating covid-19: Beyond the hype. Fron- tiers in Artificial Intelligence 4 (2021). 10.1109/LifeTech53646.2022.9754850

2021 Ahmed, I., Ahmad, M., Rodrigues, J.J., Jeon, G., Din, S.: A deep learningbased social distance monitoring framework for covid-19. Sustainable Cities and Society 65, 102571 (2021).

2021 Rahman, Tawsifur, et al. "Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images." Computers in biology and medicine 132 (2021): 104319.

2021 Phea, Sinchhean, et al. "Optimization and Implementation of a Collaborative Learning Algorithm for an AI-Enabled Real-time Biomedical System." SHS Web of Conferences. Vol. 102. EDP Sciences, 2021.

2021 Nakamura, Miyuka, et al. "Comprehensive Study of Coronavirus Disease 2019 (COVID-19) Classification based on Deep Convolution Neural Networks." SHS Web of Conferences. Vol. 102. EDP Sciences, 2021.

2021 Jain, Rachna, et al. "Deep learning based detection and analysis of COVID-19 on chest X-ray images." Applied Intelligence 51.3 (2021): 1690-1700.

2021 Abbas, Asmaa, Mohammed M. Abdelsamea, and Mohamed Medhat Gaber. "Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network." Applied Intelligence 51.2 (2021): 854-864.

2020 Cohen, Joseph Paul, et al. "Covid-19 image data collection: Prospective predictions are the future." arXiv preprint arXiv:2006.11988 (2020).

2020 Apostolopoulos, Ioannis D., and Tzani A. Mpesiana. "Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks." Physical and engineering sciences in medicine 43.2 (2020): 635-640.

2020 MZ, Che Azemin, et al. "COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings." International Journal of Biomedical Imaging 2020 (2020): 8828855-8828855.

2020 Han, Rui, et al. "Early clinical and CT manifestations of coronavirus disease 2019 (COVID-19) pneumonia." AJR Am J Roentgenol 215.2 (2020): 338-43.

2020 Lin, Tsung-Chieh, and Hsi-Chieh Lee. "Covid-19 chest radiography images analysis based on integration of image preprocess, guided grad-CAM, machine learning and risk management." Proceedings of the 4th International Conference on Medical and Health Informatics. 2020.

2019 Han, Rui, et al. "Early clinical and CT manifestations of coronavirus disease 2019 (COVID-19) pneumonia." AJR Am J Roentgenol 215.2 (2020): 338-43.

↑

Block chain†

2020 Zhuang, Yan, et al. "A patient-centric health information exchange framework using blockchain technology." IEEE journal of biomedical and health informatics 24.8 (2020): 2169-2176.

2019 Lu, Yunlong, et al. "Blockchain and federated learning for privacy-preserved data sharing in industrial IoT." IEEE Transactions on Industrial Informatics 16.6 (2019): 4177-4186.

2017 McMahan, Brendan, et al. "Communication-efficient learning of deep networks from decentralized data." Artificial intelligence and statistics. PMLR, 2017.

↑

Hardware Acceleration of ANN†

2021 Goel, Garvit, et al. "ComputeCOVID19+: Accelerating COVID-19 diagnosis and monitoring via high-performance deep Learning on CT images." 50th International Conference on Parallel Processing. 2021.

2019 Sun, Yuxi, Akram Ben Ahmed, and Hideharu Amano. "Acceleration of deep recurrent neural networks with an fpga cluster." Proceedings of the 10th International Symposium on Highly-Efficient Accelerators and Reconfigurable Technologies. 2019.

2016 Zhao, Wenlai, et al. "F-CNN: An FPGA-based framework for training convolutional neural networks." 2016 IEEE 27Th international conference on application-specific systems, architectures and processors (ASAP). IEEE, 2016.

2016 Chen, Yu-Hsin, et al. "Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks." IEEE journal of solid-state circuits 52.1 (2016): 127-138.

↑

Learning†

2020 Wang, Jun, et al. "Prior-attention residual learning for more discriminative COVID-19 screening in CT images." IEEE Transactions on Medical Imaging 39.8 (2020): 2572-2583.

2021 Muhammad, L. J., et al. "Supervised machine learning models for prediction of COVID-19 infection using epidemiology dataset." SN computer science 2.1 (2021): 1-13.

2017 Lee, Sunwoo, et al. "Parallel deep convolutional neural network training by exploiting the overlapping of computation and communication." 2017 IEEE 24th International Conference on High Performance Computing (HiPC). IEEE, 2017.

↑

Neuromorphic system in HW†

2021 Ikechukwu, Ogbodo Mark, Khanh N. Dang, and Abderazek Ben Abdallah. "On the design of a fault-tolerant scalable three dimensional NoC-based digital neuromorphic system with on-chip learning." IEEE Access 9 (2021): 64331-64345.

2020 Song, Shihao, et al. "Compiling spiking neural networks to neuromorphic hardware." The 21st ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems. 2020.

2020 Azghadi, Mostafa Rahimi, et al. "Hardware implementation of deep network accelerators towards healthcare and biomedical applications." IEEE Transactions on Biomedical Circuits and Systems 14.6 (2020): 1138-1159.

2019 Frenkel, Charlotte, Jean-Didier Legat, and David Bol. "MorphIC: A 65-nm 738k-Synapse/mm $^ 2$ quad-core binary-weight digital neuromorphic processor with stochastic spike-driven online learning." IEEE transactions on biomedical circuits and systems 13.5 (2019): 999-1010.

2019 Bhanu, P. Veda, and Pranav Venkatesh Kulkarni. "Fault-tolerant network-on-chip design with flexible spare core placement." ACM Journal on Emerging Technologies in Computing Systems (JETC) 15.1 (2019): 1-23.

2018 Frenkel, Charlotte, et al. "A 0.086-mm $^ 2 $12.7-pJ/SOP 64k-synapse 256-neuron online-learning digital spiking neuromorphic processor in 28-nm CMOS." IEEE transactions on biomedical circuits and systems 13.1 (2018): 145-158.

2018 Bhanu, P. Veda, et al. "Torus topology based fault-tolerant network-on-chip design with flexible spare core placement." 2018 14th Conference on Ph. D. Research in Microelectronics and Electronics (PRIME). IEEE, 2018.

2015 Akopyan, Filipp, et al. "Truenorth: Design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip." IEEE transactions on computer-aided design of integrated circuits and systems 34.10 (2015): 1537-1557.

↑

Mapping†

2019 Balaji, Adarsha, et al. "Mapping spiking neural networks to neuromorphic hardware." IEEE Transactions on Very Large Scale Integration (VLSI) Systems 28.1 (2019): 76-86.

2018 Geng, Tong, et al. "FPDeep: Acceleration and load balancing of CNN training on FPGA clusters." 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). IEEE, 2018.

↑

Links†

EMG Gesture recognition database: The largest and most complete dataset for EMG gesture recognition Characterization of a Benchmark Database for Myoelectric Movement Classification
My Shared GoogleDrive