A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers
Abstract
Current deep learning approaches have been very successful using convolutional neural networks trained on large graphical-processing-unit-based computers. Three limitations of this approach are that (1) they are based on a simple layered network topology, i.e., highly connected layers, without intra-layer connections; (2) the networks are manually configured to achieve optimal results, and (3) the implementation of the network model is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. We use the MNIST dataset for our experiment, due to input size limitations of current quantum computers. Our results show the feasibility of using the three architectures in tandem to address the above deep learning limitations. Finally, we show that a quantum computer can find high quality values of intra-layer connection weights in a tractable time as the complexity of the network increases, a high performance computer can find optimal layer-based topologies, and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.
- Authors:
-
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Computational Data Analytics Group
- Univ. of Southern California, Marina del Rey, CA (United States). Information Sciences Inst.
- Univ. of Tennessee, Knoxville, TN (United States). Dept. of Electrical Engineering and Computer Science
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF)
- Sponsoring Org.:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
- OSTI Identifier:
- 1474723
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- ACM Journal on Emerging Technologies in Computing Systems
- Additional Journal Information:
- Journal Volume: 14; Journal Issue: 2; Journal ID: ISSN 1550-4832
- Publisher:
- Association for Computing Machinery
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; deep learning; quantum computing; neuromorphic computing; high-performance computing
Citation Formats
Potok, Thomas E., Schuman, Catherine, Young, Steven, Patton, Robert, Spedalieri, Federico, Liu, Jeremy, Yao, Ke-Thia, Rose, Garrett, and Chakma, Gangotree. A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers. United States: N. p., 2018.
Web. doi:10.1145/3178454.
Potok, Thomas E., Schuman, Catherine, Young, Steven, Patton, Robert, Spedalieri, Federico, Liu, Jeremy, Yao, Ke-Thia, Rose, Garrett, & Chakma, Gangotree. A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers. United States. https://doi.org/10.1145/3178454
Potok, Thomas E., Schuman, Catherine, Young, Steven, Patton, Robert, Spedalieri, Federico, Liu, Jeremy, Yao, Ke-Thia, Rose, Garrett, and Chakma, Gangotree. Fri .
"A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers". United States. https://doi.org/10.1145/3178454. https://www.osti.gov/servlets/purl/1474723.
@article{osti_1474723,
title = {A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers},
author = {Potok, Thomas E. and Schuman, Catherine and Young, Steven and Patton, Robert and Spedalieri, Federico and Liu, Jeremy and Yao, Ke-Thia and Rose, Garrett and Chakma, Gangotree},
abstractNote = {Current deep learning approaches have been very successful using convolutional neural networks trained on large graphical-processing-unit-based computers. Three limitations of this approach are that (1) they are based on a simple layered network topology, i.e., highly connected layers, without intra-layer connections; (2) the networks are manually configured to achieve optimal results, and (3) the implementation of the network model is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. We use the MNIST dataset for our experiment, due to input size limitations of current quantum computers. Our results show the feasibility of using the three architectures in tandem to address the above deep learning limitations. Finally, we show that a quantum computer can find high quality values of intra-layer connection weights in a tractable time as the complexity of the network increases, a high performance computer can find optimal layer-based topologies, and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.},
doi = {10.1145/3178454},
journal = {ACM Journal on Emerging Technologies in Computing Systems},
number = 2,
volume = 14,
place = {United States},
year = {Fri Jul 27 00:00:00 EDT 2018},
month = {Fri Jul 27 00:00:00 EDT 2018}
}
Web of Science
Works referenced in this record:
A Learning Algorithm for Boltzmann Machines*
journal, January 1985
- Ackley, David H.; Hinton, Geoffrey E.; Sejnowski, Terrence J.
- Cognitive Science, Vol. 9, Issue 1
What is the best multi-stage architecture for object recognition?
conference, September 2009
- Jarrett, Kevin; Kavukcuoglu, Koray; Ranzato, Marc' Aurelio
- 2009 IEEE 12th International Conference on Computer Vision (ICCV)
High switching endurance in TaOx memristive devices
journal, December 2010
- Yang, J. Joshua; Zhang, M. -X.; Strachan, John Paul
- Applied Physics Letters, Vol. 97, Issue 23
Harmonica: A Framework of Heterogeneous Computing Systems With Memristor-Based Neuromorphic Computing Accelerators
journal, May 2016
- Liu, Xiaoxiao; Mao, Mengjie; Liu, Beiye
- IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 63, Issue 5
Neuromorphic architectures for spiking deep neural networks
conference, December 2015
- Indiveri, Giacomo; Corradi, Federico; Qiao, Ning
- 2015 IEEE International Electron Devices Meeting (IEDM)
Spatiotemporal Classification Using Neuroscience-Inspired Dynamic Architectures
journal, January 2014
- Schuman, Catherine D.; Birdwell, J. Douglas; Dean, Mark E.
- Procedia Computer Science, Vol. 41
Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores
conference, August 2013
- Cassidy, Andrew S.; Merolla, Paul; Arthur, John V.
- 2013 International Joint Conference on Neural Networks (IJCNN 2013 - Dallas), The 2013 International Joint Conference on Neural Networks (IJCNN)
Quantum annealing with manufactured spins
journal, May 2011
- Johnson, M. W.; Amin, M. H. S.; Gildert, S.
- Nature, Vol. 473, Issue 7346
Training and operation of an integrated neuromorphic network based on metal-oxide memristors
journal, May 2015
- Prezioso, M.; Merrikh-Bayat, F.; Hoskins, B. D.
- Nature, Vol. 521, Issue 7550
Extending SpikeProp
conference, January 2004
- Schrauwen, B.; Van Campenhout, J.
- 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)
Simulating physics with computers
journal, June 1982
- Feynman, Richard P.
- International Journal of Theoretical Physics, Vol. 21, Issue 6-7
Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing
conference, July 2015
- Diehl, Peter U.; Neil, Daniel; Binas, Jonathan
- 2015 International Joint Conference on Neural Networks (IJCNN)
ImageNet Large Scale Visual Recognition Challenge
journal, April 2015
- Russakovsky, Olga; Deng, Jia; Su, Hao
- International Journal of Computer Vision, Vol. 115, Issue 3
Darwin: a neuromorphic hardware co-processor based on Spiking Neural Networks
journal, December 2015
- Shen, Juncheng; Ma, De; Gu, Zonghua
- Science China Information Sciences, Vol. 59, Issue 2
Nanoscale Memristor Device as Synapse in Neuromorphic Systems
journal, April 2010
- Jo, Sung Hyun; Chang, Ting; Ebong, Idongesit
- Nano Letters, Vol. 10, Issue 4, p. 1297-1301
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
conference, December 2015
- He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
- 2015 IEEE International Conference on Computer Vision (ICCV)
A Fast Learning Algorithm for Deep Belief Nets
journal, July 2006
- Hinton, Geoffrey E.; Osindero, Simon; Teh, Yee-Whye
- Neural Computation, Vol. 18, Issue 7
Error-backpropagation in temporally encoded networks of spiking neurons
journal, October 2002
- Bohte, Sander M.; Kok, Joost N.; La Poutré, Han
- Neurocomputing, Vol. 48, Issue 1-4
A Functional Hybrid Memristor Crossbar-Array/CMOS System for Data Storage and Neuromorphic Applications
journal, December 2011
- Kim, Kuk-Hwan; Gaba, Siddharth; Wheeler, Dana
- Nano Letters, Vol. 12, Issue 1
Reducing the Dimensionality of Data with Neural Networks
journal, July 2006
- Hinton, G. E.
- Science, Vol. 313, Issue 5786
DANNA: A neuromorphic software ecosystem
journal, July 2016
- Disney, Adam; Reynolds, John; Schuman, Catherine D.
- Biologically Inspired Cognitive Architectures, Vol. 17
Circuit Techniques for Online Learning of Memristive Synapses in CMOS-Memristor Neuromorphic Systems
conference, January 2017
- Sayyaparaju, Sagarvarma; Chakma, Gangotree; Amer, Sherif
- Proceedings of the on Great Lakes Symposium on VLSI 2017 - GLSVLSI '17
Optimizing deep learning hyper-parameters through an evolutionary algorithm
conference, January 2015
- Young, Steven R.; Rose, Derek C.; Karnowski, Thomas P.
- Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments - MLHPC '15
FaceNet: A unified embedding for face recognition and clustering
conference, June 2015
- Schroff, Florian; Kalenichenko, Dmitry; Philbin, James
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
How We Found The Missing Memristor
journal, December 2008
- Williams, R.
- IEEE Spectrum, Vol. 45, Issue 12
Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
journal, August 2016
- Benedetti, Marcello; Realpe-Gómez, John; Biswas, Rupak
- Physical Review A, Vol. 94, Issue 2
Building block of a programmable neuromorphic substrate: A digital neurosynaptic core
conference, June 2012
- Arthur, John V.; Merolla, Paul A.; Akopyan, Filipp
- 2012 International Joint Conference on Neural Networks (IJCNN 2012 - Brisbane), The 2012 International Joint Conference on Neural Networks (IJCNN)
A Memristor Crossbar Based Computing Engine Optimized for High Speed and Accuracy
conference, July 2016
- Liu, Chenchen; Yang, Qing; Yan, Bonan
- 2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)
Long Short-Term Memory
journal, November 1997
- Hochreiter, Sepp; Schmidhuber, Jürgen
- Neural Computation, Vol. 9, Issue 8
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
Lognormal switching times for titanium dioxide bipolar memristors: origin and resolution
journal, January 2011
- Medeiros-Ribeiro, Gilberto; Perner, Frederick; Carter, Richard
- Nanotechnology, Vol. 22, Issue 9
Competitive Hebbian learning through spike-timing-dependent synaptic plasticity
journal, September 2000
- Song, Sen; Miller, Kenneth D.; Abbott, L. F.
- Nature Neuroscience, Vol. 3, Issue 9
Darwin: A neuromorphic hardware co-processor based on spiking neural networks
journal, June 2017
- Ma, De; Shen, Juncheng; Gu, Zonghua
- Journal of Systems Architecture, Vol. 77
ImageNet Large Scale Visual Recognition Challenge
text, January 2015
- Jia, Deng,; Andrej, Karpathy,; Sean, Ma,
- The University of North Carolina at Chapel Hill University Libraries
Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing
text, January 2015
- Diehl, P. U.; Neil, D.; Binas, J.
- Neural Networks (IJCNN), 2015 International Joint Conference on
Neuromorphic Architectures for Spiking Deep Neural Networks
text, January 2015
- Indiveri, G.; Corradi, F.; Qiao, N.
- Proceedings of International Electron Devices Meeting 2015
Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors
text, January 2014
- Prezioso, Mirko; Merrikh-Bayat, Farnood; Hoskins, Brian
- arXiv
Works referencing / citing this record:
Performance analysis and optimization for scalable deployment of deep learning models for country‐scale settlement mapping on Titan supercomputer
journal, May 2019
- Kurte, Kuldeep; Sanyal, Jibonananda; Berres, Anne
- Concurrency and Computation: Practice and Experience, Vol. 31, Issue 20
Quantum machine learning with D‐wave quantum computer
journal, June 2019
- Hu, Feng; Wang, Ban‐Nan; Wang, Ning
- Quantum Engineering, Vol. 1, Issue 2
Reliability of analog resistive switching memory for neuromorphic computing
journal, March 2020
- Zhao, Meiran; Gao, Bin; Tang, Jianshi
- Applied Physics Reviews, Vol. 7, Issue 1
Intelligent video surveillance: a review through deep learning techniques for crowd analysis
journal, June 2019
- Sreenu, G.; Saleem Durai, M. A.
- Journal of Big Data, Vol. 6, Issue 1