Neuromorphic Hardware System for Visual Pattern Recognition With Memristor Array and CMOS Neuron
The DOI matches its Crossref record; 24 of the 25 references it cites were found in a registry or an index.
Abstract
This paper presents a neuromorphic system for visual pattern recognition realized in hardware. A new learning rule based on modified spike-timing-dependent plasticity is also presented and implemented with passive synaptic devices. The system includes an artificial photoreceptor, a Pr0.7Ca0.3MnO3-based memristor array, and CMOS neurons. The artificial photoreceptor consisting of a CMOS image sensor and a field-programmable gate array converts an image into spike signals, and the memristor array is used to adjust the synaptic weights between the input and output neurons according to the learning rule. A leaky integrate-and-fire model is used for the output neuron that is built together with the image sensor on a single chip. The system has 30 input neurons that are interconnected to 10 output neurons through 300 memristors. Each input neuron corresponding to a pixel in a 5 × 6 pixel image generates voltage pulses according to the pixel value. The voltage pulses are then weighted and integrated by the memristors and the output neurons, respectively, to be compared with a certain threshold voltage above which an output neuron fires. The system has been successfully demonstrated by training and recognizing number images from 0 to 9.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Both cases consider an FPGA in order interface the image acquisition system (i.e. CMOS image sensor and the resizing algorithm) with the memristor crossbar and its peripheral circuitry.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [84]
In the citing paper
“For instance, ref. 84 uses a 480×330 pixel image sensor, with each pixel consisting of a photo diode and four transistors that generates an analogue signal whose amplitude is proportional to the light intensity. Then a 5×6 pixel binary image is generated by mapping 96×55 neighbourhood pixels into one pixel in the binary image.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [84]
Citations
Cites
Strukov, D. B., Snider, G. S., Stewart, D. R., & Williams, R. S. (2008) · Nature · doi:10.1038/nature06932 · Cited by 11,828 · cited 1×
“For example, instead of using a physical memristor device, a TiO2 memristor model proposed by Hewlett-Packard Company [20] was used in [16] and [17], and a simple variable resistor model was used in [18] and [19].”
MethodMemristive devices and systems
Chua, L. O., & Kang, S. M. (1976) · Proceedings of the IEEE · doi:10.1109/proc.1976.10092 · Cited by 2,604 · cited 1×
“A memristor is a two-terminal passive device that modifies or retains its resistance according to the time integral of the current flowing through it [22].”
BackgroundResistance switching memories are memristors
Chua, L. (2011) · Applied Physics A · doi:10.1007/s00339-011-6264-9 · Cited by 1,434
Indiveri, G., Chicca, E., & Douglas, R. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.860850 · Cited by 1,009 · cited 1×
“Recent developments in CMOS technology allow the largescale integration of integrate-and-fire (I&F) neurons on a single chip [9]–[12].”
BackgroundSpike-timing-dependent synaptic modification induced by natural spike trains
Froemke, R. C., & Dan, Y. (2002) · Nature · doi:10.1038/416433a · Cited by 803
A comprehensive review for industrial applicability of artificial neural networks
Meireles, M. R. G., Almeida, P. E. M., & Simoes, M. G. (2003) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2003.812470 · Cited by 482
Memristor Bridge Synapse-Based Neural Network and Its Learning
Adhikari, S. P., Yang, C., Kim, H., & Chua, L. O. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2204770 · Cited by 386 · cited 2×
“For example, instead of using a physical memristor device, a TiO2 memristor model proposed by Hewlett-Packard Company [20] was used in [16] and [17], and a simple variable resistor model was used in [18] and [19].”
MethodNeural Synaptic Weighting With a Pulse-Based Memristor Circuit
Kim, H., Sah, M. P., Yang, C., Roska, T., & Chua, L. O. (2012) · IEEE Transactions on Circuits and Systems I: Regular Papers · doi:10.1109/tcsi.2011.2161360 · Cited by 348 · cited 4×
“For example, instead of using a physical memristor device, a TiO2 memristor model proposed by Hewlett-Packard Company [20] was used in [16] and [17], and a simple variable resistor model was used in [18] and [19].”
BackgroundMethodInfluentialSeo, J.-S., Brezzo, B., Liu, Y., Parker, B. D., Esser, S. K., Montoye, R. K., Rajendran, B., Tierno, J. A., Chang, L., Modha, D. S., et al. (2011) · 2011 IEEE Custom Integrated Circuits Conference (CICC) · doi:10.1109/cicc.2011.6055293 · Cited by 344
Real-Time Classification of Complex Patterns Using Spike-Based Learning in Neuromorphic VLSI
Mitra, S., Fusi, S., & Indiveri, G. (2009) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2008.2005781 · Cited by 238
Chicca, E., Badoni, D., Dante, V., D'Andreagiovanni, M., Salina, G., Carota, L., Fusi, S., & Del Giudice, P. (2003) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2003.816367 · Cited by 211 · cited 1×
“Recent developments in CMOS technology allow the largescale integration of integrate-and-fire (I&F) neurons on a single chip [9]–[12].”
BackgroundCantley, K. D., Subramaniam, A., Stiegler, H. J., Chapman, R. A., & Vogel, E. M. (2011) · IEEE Transactions on Nanotechnology · doi:10.1109/tnano.2011.2105887 · Cited by 159 · cited 1×
“For example, instead of using a physical memristor device, a TiO2 memristor model proposed by Hewlett-Packard Company [20] was used in [16] and [17], and a simple variable resistor model was used in [18] and [19].”
MethodAnalog VLSI Circuit Implementation of an Adaptive Neuromorphic Olfaction Chip
Koickal, T. J., Hamilton, A., Tan, S. L., Covington, J. A., Gardner, J. W., & Pearce, T. C. (2007) · IEEE Transactions on Circuits and Systems I: Regular Papers · doi:10.1109/tcsi.2006.888677 · Cited by 153
Synchrony Detection and Amplification by Silicon Neurons With STDP Synapses
Bofill-i-Petit, A., & Murray, A. F. (2004) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.832842 · Cited by 144
Nanoscale RRAM-based synaptic electronics: toward a neuromorphic computing device
Park, S., Noh, J., Choo, M.-L., Sheri, A. M., Chang, M., Kim, Y.-B., Kim, C. J., Jeon, M., Lee, B.-G., Lee, B. H., et al. (2013) · Nanotechnology · doi:10.1088/0957-4484/24/38/384009 · Cited by 139
Self-citationA Learning-Enabled Neuron Array IC Based Upon Transistor Channel Models of Biological Phenomena
Brink, S., Nease, S., Hasler, P. E., Ramakrishnan, S., Wunderlich, R. B., Basu, A., & Degnan, B. P. (2012) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2012.2197858 · Cited by 131
Neural Learning Circuits Utilizing Nano-Crystalline Silicon Transistors and Memristors
Cantley, K. D., Subramaniam, A., Stiegler, H. J., Chapman, R. A., & Vogel, E. M. (2012) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2184801 · Cited by 121 · cited 3×
“For example, instead of using a physical memristor device, a TiO2 memristor model proposed by Hewlett-Packard Company [20] was used in [16] and [17], and a simple variable resistor model was used in [18] and [19].”
BackgroundMethodMultichannel Pulse-Coupled-Neural-Network-Based Color Image Segmentation for Object Detection
Zhuang, H., Low, K., & Yau, W. (2011) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2011.2165451 · Cited by 84
Rubaai, A., Castro-Sitiriche, M. J., Garuba, M., & Burge, L. (2007) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2006.888785 · Cited by 46
A Pulsed Neural Network With On-Chip Learning and Its Practical Applications
Zhuang, H., Low, K., & Yau, W. (2007) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2006.888684 · Cited by 37 · cited 1×
“The hardware implementation of spiking neural networks has been an active research field, and recent publications [5]–[8] have proven the feasibility of applying neural networks for some industrial applications such as the signal processing of complex data sets.”
BackgroundLi, T.-Y., Tsai, J.-Z., Chang, R.-S., Ho, L.-W., & Yang, C.-F. (2013) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2012.2207658 · Cited by 35 · cited 1×
“AN artificial neural network (ANN) is a computational model inspired by the neocortex of human brain that is capable of solving a variety of problems in recognition, prediction, optimization, and control [1]–[4].”
BackgroundChicca, E., Indiveri, G., & Douglas, R. J. (2003) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2003.1205505 · Cited by 35
Moreno, F., Alarcon, J., Salvador, R., & Riesgo, T. (2009) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2009.2022076 · Cited by 32 · cited 1×
“The hardware implementation of spiking neural networks has been an active research field, and recent publications [5]–[8] have proven the feasibility of applying neural networks for some industrial applications such as the signal processing of complex data sets.”
BackgroundEberhardt, S. P., Tawel, R., Brown, T. X., Daud, T., & Thakoor, A. P. (1992) · IEEE Transactions on Industrial Electronics · doi:10.1109/41.170975 · Cited by 30 · cited 1×
“However, the CMOS implementation of synaptic circuits requires a large number of transistors and a considerable amount of power consumption [13]–[15].”
Background
Cited by
Near-sensor and in-sensor computing
Zhou, F., & Chai, Y. (2020) · Nature Electronics · doi:10.1038/s41928-020-00501-9 · Cited by 1,090
A Survey of Neuromorphic Computing and Neural Networks in Hardware
Schuman, C. D., Potok, T. E., Patton, R. M., Birdwell, J. D., Dean, M. E., Rose, G. S., & Plank, J. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.06963 · Cited by 352
“[1130], [1149], [1380], [1415], [1446], [1798], [1819], [1852],”
Dynamical memristors for higher-complexity neuromorphic computing
Kumar, S., Wang, X., Strachan, J. P., Yang, Y., & Lu, W. D. (2022) · Nature Reviews Materials · doi:10.1038/s41578-022-00434-z · Cited by 558
“Panel a adapted with permission from ref.(131), IEEE.”
BackgroundHardware implementation of memristor-based artificial neural networks
Aguirre, F., Sebastian, A., Le Gallo, M., Song, W., Wang, T., Yang, J. J., Lu, W., Chang, M.-F., Ielmini, D., Yang, Y., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-45670-9 · Cited by 564
An Artificial Neuron Based on a Threshold Switching Memristor
Zhang, X., Wang, W., Liu, Q., Zhao, X., Wei, J., Cao, R., Yao, Z., Zhu, X., Zhang, F., Lv, H., et al. (2018) · IEEE Electron Device Letters · doi:10.1109/led.2017.2782752 · Cited by 407
“The input images are 5×6 pixels [21].”
Metadata
- Authors
- Chu, M., Kim, B., Park, S., Hwang, H., Jeon, M., Lee, B. H., & Lee, B.-G.
- Affiliations
- Gwangju Institute of Science and Technology (KR)
- Pohang University of Science and Technology (KR)
- Venue
- IEEE Transactions on Industrial Electronics
- Published
- 2015-04
- Volume
- 62
- Issue
- 4
- Pages
- 2410-2419
- ISSN
- 0278-0046 (ISSN-L)
- 1557-9948
- OpenAlex
- W2132563832
- Semantic Scholar
- 1565d19efe8150c7b363526f7fe678b6f57469d0
- Cited by
- 296
- References
- 25
- Citations by year
- 2026: 10 · 2025: 12 · 2024: 27 · 2023: 31 · 2022: 37 · 2021: 34 · 2020: 25 · 2019: 34 · 2018: 31 · 2017: 25 · 2016: 22 · 2015: 7
- FWCI
- 9.56
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Industrial Electronics (publishedVersion)
- Open Access System for Information Sharing (Pohang University of Science and Technology) (submittedVersion)
- Funders
- Pioneer Research Center Program through the National Research Foundation of Korea funded by the Ministry of Science, ICT and Future Planning (2012-0009460)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- neuromorphic hardware, visual pattern recognition, memristor arrays, spike-timing-dependent plasticity, learning rules, CMOS image sensor, FPGA, leaky integrate-and-fire neurons, Pr0.7Ca0.3MnO3, number recognition, on-chip image processing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.