The DOI matches its Crossref record; 18 of the 19 references it cites were found in a registry or an index; 2 of the 10 sources its claims cite were checked for support.
Linking Conductive Filament Properties and Evolution to Synaptic Behavior of RRAM Devices for Neuromorphic Applications
Open accessAbstract
We perform a comparative study of HfO2and Ta2O5resistive switching memory (RRAM) devices for their possible application as electronic synapses. By means of electrical characterization and simulations, we link their electrical behavior (digital or analog switching) to the properties and evolution of the conductive filament (CF). More specifically, we identify that bias-polarity-dependent digital switching in HfO2RRAM is primarily related to the creation and rupture of an oxide barrier. Conversely, the modulation of the CF size in Ta2O5RRAM allows bias-polarity-independent analog switching with multiple states. Therefore, when the Ta2O5RRAM is used to implement a synapse in multilayer perceptron neural networks operated by back-propagation algorithms, patterns in handwritten digits can be recognized with high accuracy.
Overview
CoChat Summary
TL;DR
A comparative study of HfO₂ and Ta₂O₅ RRAM devices links their digital versus analog switching to the properties and evolution of the conductive filament (CF), using electrical characterization plus simulations. The Ta₂O₅ device's CF-size modulation yields bias-polarity-independent analog switching with multiple states, which the authors use as synapses in a multilayer perceptron for MNIST digit recognition.
Key findings
- HfO₂ RRAM shows bias-polarity-dependent digital switching: SET is abrupt and RESET gradual, and identical SET pulses at fixed Vg = 1.2 V produce binary states with current saturation after the first pulse; only varying Vg from 0.6 to 1.2 V splits the binary states into multiple states.
- Simulations attribute this to the creation and rupture of an oxide barrier (δ ≈ 1.5–2 nm after RESET); current depends exponentially on a large δ (> 1 nm) but linearly on CF size, and the field after CF restoration (~1.7 MV/cm) is far below the ~4–5 MV/cm needed to break Hf–O bonds.
- Ta₂O₅ (TiOx/Ta₂O₅) RRAM shows bias-polarity-independent analog switching: 100 identical positive pulses (2–3.5 V, 10 µs) and 100 negative pulses (−3 to −5 V, 100 µs) monotonically tune current, because RESET modulates CF width rather than forming a barrier — aided by oxygen diffusion in Ta₂O₅ with activation energy ~1.2 eV.
- In MNIST pattern recognition with a multilayer perceptron (528 input neurons from a cropped 22 × 24 image, back-propagation), HfO₂ binary-state synapses reached 94% accuracy in off-chip learning, while Ta₂O₅ linearly modulated multiple states enabled 88% accuracy during on-chip learning.
Methods
- Comparative device study: Ti TE (15 nm)/HfO₂ (6 nm)/TiN BE (400 nm) connected to a 0.35 µm transistor, versus bilayered TiOx/Ta₂O₅ sandwiched between TiN BE/TE with TiOx as an oxygen reservoir.
- Electrical characterization (I-V cycling, identical and non-identical pulse trains, compliance-current ramping) combined with simulations using the Ginestra™ package, which self-consistently models charge transport, power dissipation, temperature rise, and oxygen ion/vacancy generation, diffusion, and recombination.
- Neural-network evaluation: MNIST handwritten digits in a multilayer perceptron (input, hidden, output layers) with synaptic weight taken as the conductance difference of a pair of RRAM devices, updated by back-propagation.
Limitations
- The paper states no explicit limitations.
- Evident from the text: the two accuracy figures come from different learning schemes (94% for HfO₂ in off-chip learning versus 88% for Ta₂O₅ in on-chip learning), so they are not a like-for-like comparison, and the Ta₂O₅ result is numerically lower despite being presented as the improvement.
- Evident from the text: the pattern-recognition results are simulation-based, and the device comparison covers only two material stacks without reported endurance, variability, or retention statistics beyond the 100 switching cycles shown.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 1 Not valid · 5 Not checked · 15 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The data could be recognized more precisely using the linearly modulated multiple states in the Ta2O5 RRAM based synapses in neuromorphic systems, thereby enabling improved accuracy (88%) of pattern recognition.”
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In this case, the synapses with binary states had limitations in improving the recognition accuracy.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Therefore, when the Ta2O5 RRAM is used to implement a synapse in multilayer perceptron neural networks operated by back-propagation algorithms, patterns in handwritten digits can be recognized with high accuracy.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Simulation results clearly show that the RESET operation leads to a modulation of the CF size rather than to the creation of the δ , see Fig. 5(e).”
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“Once the CF is recreated, the electric field is approximately equal to VP/tOX ∼ 1.7 MV/cm (being tOX the HfO2 thickness), which is far lower than the critical field of ∼ 4-5 MV/cm needed to break Hf-O bonds [15].”
What the sources say
- Not checked — no full text of the sourcecites [15] [15] M. Alayan, E. Vianello, B. De Salvo, L. Perniola, A. Padovani, and L. Larcher, 'Correlated Effects on Forming and Retention of Al Doping in 16. HfO2-Based RRAM,' IEEE Design & Test , vol. 34, no. 3, June 2017. DOI: 10.1109/MDAT.2017.2682246 - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
8 more claims
Create a free account to see all 22 claims and every source verdict.
- Probably not a substantial claim. 1
- It may state two separate claims as one. 9
- The quote only partly states this claim. 1
Citations
Cites
A million spiking-neuron integrated circuit with a scalable communication network and interface
Merolla, P. A., Arthur, J. V., Alvarez-Icaza, R., Cassidy, A. S., Sawada, J., Akopyan, F., Jackson, B. L., Imam, N., Guo, C., Nakamura, Y., et al. (2014) · Science · doi:10.1126/science.1254642 · Cited by 4,147
Neuromorphic electronic systems
Mead, C. (1990) · Proceedings of the IEEE · doi:10.1109/5.58356 · Cited by 2,368 · cited 1×
“They follow a simple weight update rule through synapses, similar to how humans remember information [2].”
BackgroundBurr, G. W., Shelby, R. M., Sidler, S., di Nolfo, C., Jang, J., Boybat, I., Shenoy, R. S., Narayanan, P., Virwani, K., Giacometti, E. U., et al. (2015) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2015.2439635 · Cited by 936
Self-citationWoo, J., Moon, K., Song, J., Lee, S., Kwak, M., Park, J., & Hwang, H. (2016) · IEEE Electron Device Letters · doi:10.1109/led.2016.2582859 · Cited by 512 · cited 1×
“A 15-nm-thick Ti top electrode (TE) was then deposited, resulting in Ti TE/HfO2/TiN BE stack [7].”
BackgroundSelf-citationSpin-Transfer Torque Magnetic Memory as a Stochastic Memristive Synapse for Neuromorphic Systems
Vincent, A. F., Larroque, J., Locatelli, N., Ben Romdhane, N., Bichler, O., Gamrat, C., Zhao, W. S., Klein, J.-O., Galdin-Retailleau, S., & Querlioz, D. (2015) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2015.2414423 · Cited by 360
Optimization of Conductance Change in Pr1–xCaxMnO3-Based Synaptic Devices for Neuromorphic Systems
Jang, J.-W., Park, S., Burr, G. W., Hwang, H., & Jeong, Y.-H. (2015) · IEEE Electron Device Letters · doi:10.1109/led.2015.2418342 · Cited by 310
Self-citationAmbrogio, S., Balatti, S., Milo, V., Carboni, R., Wang, Z.-Q., Calderoni, A., Ramaswamy, N., & Ielmini, D. (2016) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2016.2526647 · Cited by 256 · cited 1×
“However, many studies have reported that only two discrete states are demonstrated during potentiation, whereas depression demonstrates multiple states [9]–[11].”
BackgroundBio-Inspired Stochastic Computing Using Binary CBRAM Synapses
Suri, M., Querlioz, D., Bichler, O., Palma, G., Vianello, E., Vuillaume, D., Gamrat, C., & DeSalvo, B. (2013) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2013.2263000 · Cited by 229 · cited 1×
“phase change memory [3], [4], spin-based memory [5], and resistive switching memory (RRAM) [6]–[11].”
BackgroundMicroscopic Modeling of HfOx RRAM Operations: From Forming to Switching
Padovani, A., Larcher, L., Pirrotta, O., Vandelli, L., & Bersuker, G. (2015) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2015.2418114 · Cited by 219
Self-citationBinary neural network with 16 Mb RRAM macro chip for classification and online training
Yu, S., Li, Z., Chen, P.-Y., Wu, H., Gao, B., Wang, D., Wu, W., & Qian, H. (2016) · 2016 IEEE International Electron Devices Meeting (IEDM) · doi:10.1109/iedm.2016.7838429 · Cited by 219 · cited 1×
“6(b) [19].”
Research works printed but not linked: 1
- 2017, MDLSoft Software
Cited by
Recent progress in analog memory-based accelerators for deep learning
Tsai, H., Ambrogio, S., Narayanan, P., Shelby, R. M., & Burr, G. W. (2018) · Journal of Physics D: Applied Physics · doi:10.1088/1361-6463/aac8a5 · Cited by 225
In-memory Learning with Analog Resistive Switching Memory: A Review and Perspective
Xi, Y., Gao, B., Tang, J., Chen, A., Chang, M.-F., Hu, X. S., Spiegel, J. V. D., Qian, H., & Wu, H. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3004543 · Cited by 196
“In this section, some device optimizations and their underlying mechanisms are discussed, including electrothermal modulation [54], [141], [145], preferable locations of conductive filaments [147], interface barrier modulation [148], and optimization of cell structure [143].”
BackgroundMethodInfluentialDevice and materials requirements for neuromorphic computing
Islam, R., Li, H., Chen, P.-Y., Wan, W., Chen, H.-Y., Gao, B., Wu, H., Yu, S., Saraswat, K., & Philip Wong, H.-S. (2019) · Journal of Physics D: Applied Physics · doi:10.1088/1361-6463/aaf784 · Cited by 158
Resistive Memory-Based Analog Synapse: The Pursuit for Linear and Symmetric Weight Update
Woo, J., & Yu, S. (2018) · IEEE Nanotechnology Magazine · doi:10.1109/mnano.2018.2844902 · Cited by 139
“Physical descriptions of the filamentary rraM have recently shown how filament evolutions are linked with the synaptic characteristics, as shown in Figure 5 [42], [43].”
BackgroundSelf-citationAnalog‐Type Resistive Switching Devices for Neuromorphic Computing
Zhang, W., Gao, B., Tang, J., Li, X., Wu, W., Qian, H., & Wu, H. (2019) · physica status solidi (RRL) - Rapid Research Letters · doi:10.1002/pssr.201900204 · Cited by 132
CMOS-compatible neuromorphic devices for neuromorphic perception and computing: a review
Zhu, Y., Mao, H., Zhu, Y., Wang, X., Fu, C., Ke, S., Wan, C., & Wan, Q. C. (2023) · International Journal of Extreme Manufacturing · doi:10.1088/2631-7990/acef79 · Cited by 120
“Resistive switching devices with asymmetric and nonlinear conductance tuning characteristics can reduce the accuracy of computation [47, 48].”
BackgroundKim, H., Hwang, S., Park, J., Yun, S., Lee, J., & Park, B. (2018) · IEEE Electron Device Letters · doi:10.1109/led.2018.2809661 · Cited by 90
“There are two manners for learning in neuromorphic system and SNN: on-chip [14]–[16] and off-chip learning [17], [18].”
BackgroundFrom Memristive Materials to Neural Networks
Guo, T., Sun, B. T., Ranjan, S., Jiao, Y., Wei, L., Zhou, Y., & Wu, Y. A. (2020) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.0c10796 · Cited by 90
Rao, J., Fan, Z. H., Hong, L., Cheng, S., Huang, Q., Zhao, J., Xiang, X., Guo, E., Guo, H., Hou, Z., et al. (2021) · Materials Today Physics · doi:10.1016/j.mtphys.2021.100392 · Cited by 86
HfO x /AlO y Superlattice‐Like Memristive Synapse
Wang, C., Mao, G., Huang, M., Huang, E., Zhang, Z., Yuan, J., Cheng, W., Xue, K., Wang, X., & Miao, X. (2022) · Advanced Science · doi:10.1002/advs.202201446 · Cited by 91
Kim, G. S., Song, H., Lee, Y. K., Kim, J. H., Kim, W., Park, T. H., Kim, H. J., Min Kim, K., & Hwang, C. S. (2019) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.9b16499 · Cited by 64
Synaptic plasticity and preliminary-spike-enhanced plasticity in a CMOS-compatible Ta2O5 memristor
Hwang, H.-G., Woo, J., Lee, T., Park, S.-M., Lee, T., Lee, W.-H., & Nahm, S. (2019) · Materials & Design · doi:10.1016/j.matdes.2019.108400 · Cited by 60
Self-citationJu, D., Kim, J. H., & Kim, S. (2023) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2023.170920 · Cited by 56
Emerging memristive artificial neuron and synapse devices for the neuromorphic electronics era
Li, J., Abbas, H., Ang, D. S., Ali, A., & Ju, X. (2023) · Nanoscale Horizons · doi:10.1039/d3nh00180f · Cited by 56
Padovani, A., Woo, J., Hwang, H., & Larcher, L. (2018) · IEEE Electron Device Letters · doi:10.1109/led.2018.2821707 · Cited by 52
“native [6]–[9], with the potential to provide good analog switching characteristics at the same (area) cost of a 1T-1R”
BackgroundSelf-citationImpact of RTN on Pattern Recognition Accuracy of RRAM-Based Synaptic Neural Network
Chai, Z., Freitas, P., Zhang, W., Hatem, F. O., Zhang, J. F., Marsland, J., Govoreanu, B., Goux, L., & Kar, G. S. (2018) · IEEE Electron Device Letters · doi:10.1109/led.2018.2869072 · Cited by 54
“Both types have been intensively studied for novel synaptic applications [2]–[6], but there is a lack of comparative analysis between them.”
BackgroundChuang, K.-C., Chu, C.-Y., Zhang, H., Luo, J.-D., Li, W.-S., Li, Y.-S., & Cheng, H. (2019) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2019.2915975 · Cited by 51
Hwang, H.-G., Pyo, Y., Woo, J., Kim, I., Kim, S., Kim, D., Kim, B., Jeong, J., & Nahm, S. (2022) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2022.163764 · Cited by 48
Self-citationWoo, J., & Yu, S. (2019) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2019.2917764 · Cited by 50
“Low evolution velocity of 0.3 m/s and electric field dependence of 0.2 were empirically used because the electric field after the filament formation became lower and uniform across the oxide [30].”
BackgroundMethodInfluentialSelf-citationAsghar, M. S., Arslan, S., & Kim, H. (2021) · Sensors · doi:10.3390/s21134462 · Cited by 47
“Learning in the neuromorphic systems can be categorized into on-chip [34,35] and off-chip learning [36,37].”
BackgroundCheong, W. H., Jeon, J. B., In, J. H., Kim, G., Song, H., An, J., Park, J., Kim, Y. S., Hwang, C. S., & Kim, K. M. (2022) · Advanced Functional Materials · doi:10.1002/adfm.202200337 · Cited by 44
Analog switching characteristics in TiW/Al2O3/Ta2O5/Ta RRAM devices
Song, W., Wang, W., Lee, H. K., Li, M., Zhuo, V. Y.-Q., Chen, Z., Chui, K. J., Liu, J.-C., Wang, I., Zhu, Y. H., et al. (2019) · Applied Physics Letters · doi:10.1063/1.5100075 · Cited by 39
Tuning the analog synaptic properties of forming free SiO2 memristors by material engineering
Bousoulas, P., Sakellaropoulos, D., & Tsoukalas, D. (2021) · Applied Physics Letters · doi:10.1063/5.0044647 · Cited by 42
Ku, B., Abbas, Y., Kim, S., Sokolov, A. S., Jeon, Y.-R., & Choi, C. (2019) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2019.05.114 · Cited by 36
Resistive Switching and Synaptic Characteristics in ZnO/TaON-Based RRAM for Neuromorphic System
Oh, I., Pyo, J., & Kim, S. (2022) · Nanomaterials · doi:10.3390/nano12132185 · Cited by 35
“Multiple conductance states can be gradually increased or decreased; these are similar to potentiation and depression in a biological system, respectively [20].”
BackgroundThe resistive switching characteristics of Ni-doped HfO film and its application as a synapse
Tan, T., Du, Y., Ai, C., Sun, Y., Zha, G., Lei, H., & Zheng, X. (2018) · Journal of Alloys and Compounds · doi:10.1016/j.jallcom.2018.07.044 · Cited by 35
High-performance memristor based on MoS2 for reliable biological synapse emulation
Chen, J., Xu, J., Chen, J., Gao, L., Yang, C., Guo, T., Zhao, Y., Xiao, Y., Wang, J., & Li, Y. (2022) · Materials Today Communications · doi:10.1016/j.mtcomm.2022.103957 · Cited by 33
Liu, J., Yang, H., Ma, Z., Chen, K., Huang, X., & Wang, K. (2020) · Journal of Applied Physics · doi:10.1063/5.0024668 · Cited by 31
Composition and Surface Morphology Invariant High On–Off Ratio from an Organic Memristor
Betal, A., Bera, J., Sharma, A., Rath, A. K., & Sahu, S. (2022) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.1c01234 · Cited by 30
Stimulated Ionic Telegraph Noise in Filamentary Memristive Devices
Brivio, S., Frascaroli, J., Covi, E., & Spiga, S. (2019) · Scientific Reports · doi:10.1038/s41598-019-41497-3 · Cited by 31
Recent Advancements in Emerging Neuromorphic Device Technologies
Woo, J., Kim, J. H., Im, J., & Moon, S. E. (2020) · Advanced Intelligent Systems · doi:10.1002/aisy.202000111 · Cited by 37
Self-citationA Highly Linear Neuromorphic Synaptic Device Based on Regulated Charge Trap/Detrap
Choi, J.-M., Park, E.-J., Woo, J.-J., & Kwon, K.-W. (2019) · IEEE Electron Device Letters · doi:10.1109/led.2019.2943113 · Cited by 25
“PROMISING neuromorphic synapse candidates such as ferroelectric (FE) FET, resistive random access memory (RRAM), and charge-trap based floating gate (FG) memory have been attracting significant attention for biologically inspired intelligent systems, owing to their excellent scalability, high density, and low-power [1…”
BackgroundSelf-citationBending Resistant Multibit Memristor for Flexible Precision Inference Engine Application
Pal, P., Lee, K.-J., Thunder, S., De, S., Huang, P.-T., Kämpfe, T., & Wang, Y. (2022) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2022.3186965 · Cited by 22
Investigation of $I-V$ Linearity in TaOx-Based RRAM Devices for Neuromorphic Applications
Sung, C., Padovani, A., Beltrando, B., Lee, D., Kwak, M., Lim, S., Larcher, L., Marca, V. D., & Hwang, H. (2019) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2019.2902653 · Cited by 17
“tics achieved during potentiation or depression in the weight update operations [7]–[11].”
BackgroundSelf-citationReview of neuromorphic computing based on NAND flash memory
Lee, S., & Lee, J.-H. (2024) · Nanoscale Horizons · doi:10.1039/d3nh00532a · Cited by 22
Wang, T., Brivio, S., Cianci, E., Wiemer, C., Perego, M., Spiga, S., & Lanza, M. (2022) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.2c03364 · Cited by 21
Towards Synaptic Behavior of Nanoscale ReRAM Devices for Neuromorphic Computing Applications
Beckmann, K., Olin-Ammentorp, W., Chakma, G., Amer, S., Rose, G. S., Hobbs, C., Nostrand, J. V., Rodgers, M. P., & Cady, N. C. (2020) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3381859 · Cited by 21
Optoelectronic array of photodiodes integrated with RRAMs for energy-efficient in-sensor computing
Pan, W., Wang, L., Tang, J., Huang, H., Hao, Z., Sun, C., Xiong, B., Wang, J., Han, Y., Li, H., et al. (2025) · Light Science & Applications · doi:10.1038/s41377-025-01743-y · Cited by 30
Kang, H., Seo, J., Kim, H.-J., Kim, H. W., Hong, E. R., Kim, N., Lee, D., & Woo, J. (2022) · Micromachines · doi:10.3390/mi13030453 · Cited by 20
“This is because clustering of oxygen vacancies instantly makes a path due to the highly concentrated electric field at the small gap between the electrode and partially grown filament [13].”
BackgroundSelf-citationLarcher, L., & Padovani, A. (2017) · Journal of Computational Electronics · doi:10.1007/s10825-017-1095-3 · Cited by 19
Self-citationKim, J., Choi, J. H., Kim, S., Choi, C., & Kim, S. (2023) · Carbon · doi:10.1016/j.carbon.2023.118438 · Cited by 18
Leveraging 3D Vertical RRAM to Developing Neuromorphic Architecture for Pattern Classification
Kim, B., & Li, H. H. (2020) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi49217.2020.00054 · Cited by 17
“When V ( t ) > 0 , f ( x ( t )) is calculated by (4); otherwise, it is described by (5). x < x p and (4) where Figure 3 shows that the I-V curve produced by our model fits well with experimental measurement data of the Ta 2 O 5 RRAM device from [19].”
MethodSun, W., Choi, S., Kim, B., & Park, J. (2019) · Materials · doi:10.3390/ma12203451 · Cited by 19
“It shows that the experiment and simulation results using our model are qualitatively consistent. behavior of an experimentally measured Ta 2 O 5 memristor device [21].”
BackgroundMethodInfluentialMemristors Based on 2D Materials: Bridging Device Theory and Potential Applications
Liu, X., Pan, Z., Xia, Z., Li, L., Deng, Q., Pan, Y., Li, J., & Huo, N. (2025) · Advanced Functional Materials · doi:10.1002/adfm.202520816 · Cited by 21
Optimal Architecture of Floating-Point Arithmetic for Neural Network Training Processors
Junaid, M., Arslan, S., Lee, T., & Kim, H. (2022) · Sensors · doi:10.3390/s22031230 · Cited by 19
“As explained in [12], learning in deployed neural networks can be of two types, which are on-chip learning [13,14] and off-chip learning [15,16].”
BackgroundPal, P., Mazumder, S., Huang, C.-W., Lu, D. D., & Wang, Y. (2022) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.1c01219 · Cited by 15
Yang, Y., Zhu, X., Ma, Z., Hu, H., Chen, T., Li, W., Xu, J., Xu, L., & Chen, K. (2023) · Nanomaterials · doi:10.3390/nano13030605 · Cited by 17
High‐Performance GdNiO3 Epitaxial Film Memristor for Neuralactivity Analysis
Bai, B., Liu, G., Sun, Y., Liu, P., Zhao, Z., Guo, Z., & Yan, X. (2024) · Advanced Functional Materials · doi:10.1002/adfm.202305261 · Cited by 14
Homo-layer hafnia-based memristor with large analog switching window
Bai, N., Tian, B., Mao, G., Xue, K., Wang, T., Yuan, J., Liu, X., Li, Z., Guo, S., Zhou, Z., et al. (2021) · Applied Physics Letters · doi:10.1063/5.0032556 · Cited by 14
Multibit-Generating Pulsewidth-Based Memristive-PUF Structure and Circuit Implementation
Choi, S., Kim, D., Choi, Y., et al. (2020) · Electronics · doi:10.3390/electronics9091446 · Cited by 13
“In Figure 1b, the black diamond‐shaped values are experimental data from a Ta O memristor [21].”
MethodResultInfluentialPal, P., Thunder, S., Tsai, M.-J., Huang, P.-T., & Wang, Y. (2021) · International Symposium on VLSI Technology, Systems and Applications (VLSI-TSA) · doi:10.1109/vlsi-tsa51926.2021.9440130 · Cited by 13
“Amid a many emerging non-volatile memories (eNVMs) resistive random-access memories (RRAM) are one of the most promising candidates for neural network applications [2,3,4].”
BackgroundGarcía, H., Vinuesa, G., García-Ochoa, E., et al. (2023) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/acdae0 · Cited by 13
Graphene-based 3D XNOR-VRRAM with ternary precision for neuromorphic computing
Alimkhanuly, B., Sohn, J., Chang, I., & Lee, S. (2021) · npj 2D Materials and Applications · doi:10.1038/s41699-021-00236-x · Cited by 15
“Therefore, the Verilog-A compact model was con fi gured based on the concepts of tunneling gap evolution, accurately demonstrated in the Stanford RRAM design 38 – 41 , and conductive fi lament (CF) radial evolutions 42,43 .”
MethodImproved Resistive Switching Observed in Ti/Zr3N2/p-Si Capacitor via Hydrogen Passivation
Bae, D., Lee, D., Kim, S., & Kim, H. (2022) · IEEE Access · doi:10.1109/access.2022.3142368 · Cited by 11
Padovani, A., Pešić, M., Nardi, F., Milo, V., Larcher, L., Kumar, M. A., & Baten, M. Z. (2022) · IEEE International Reliability Physics Symposium proceedings · doi:10.1109/irps48227.2022.9764451 · Cited by 13
“RRAM stacks based on two layers have shown the best current modulation characteristics [45], [46], thanks to two main factors.”
BackgroundSelf-citationLee, C., Lee, J.-E., Kim, M.-J., Song, Y., Han, G., Seo, J., Kim, D., Seo, Y.-H., Hwang, H., & Lee, D. (2020) · Japanese Journal of Applied Physics · doi:10.35848/1347-4065/abd70d · Cited by 10
Self-citationChuang, K.-C., Lin, K., Luo, J.-D., et al. (2018) · IEEE Journal of the Electron Devices Society · doi:10.1109/jeds.2018.2832542 · Cited by 10
“Furthermore, the breakdown field of 3.48 MV/cm for the EFS-structured RRAM device indicated that the HfOx at the corner of the EFS structure was more defective than the HfOx of the planar structure.”
ResultInfluentialMa, F., Xu, Z., Liu, Y., Zheng, Y., Chen, W., Hu, H., Guo, T., Li, F., Wu, C., & Kim, T. W. (2019) · IEEE Electron Device Letters · doi:10.1109/led.2019.2934895 · Cited by 11
“However, current memristor-based artificial synapses, especially e-synapses based on conductive filament switching, [13]–[16] usually show a high degree of instability, which makes artificial intelligence systems that implement large-scale simulated neural computations impractical.”
BackgroundPhysics-based compact modelling of the analog dynamics of HfO x resistive memories
Vaccaro, F., Brivio, S., Perotto, S., Mauri, A. G., & Spiga, S. (2022) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/ac7327 · Cited by 11
“We consider RRAM devices based on filamentary switching in oxide, which have reached good maturity as binary storage elements, and which have been recently studied also as analog memories for neuromorphic computation [6, 11, 12].”
MethodIslam, R., Qin, S., Deshmukh, S., Yu, Z., Köroğlu, Ç., Khan, A. I., Schauble, K. E., Saraswat, K. C., Pop, E., & Wong, H. ‐. P. (2022) · Applied Physics Letters · doi:10.1063/5.0101417 · Cited by 9
Robust Lateral Structure Memristor Based on MoS2 Synthesized by CVD
Chen, J., Xu, J., Gao, L., Yang, C., Guo, T., Chen, J., Zhao, Y., Xiao, Y., Wang, J., & Li, Y. (2022) · Journal of Electronic Materials · doi:10.1007/s11664-022-09772-8 · Cited by 10
Pal, P., Singh, A., & Wang, Y. (2023) · Journal of Physics D Applied Physics · doi:10.1088/1361-6463/acc8e4 · Cited by 9
Spike-time-dependent plasticity rule in memristor models for circuit design
Elhamdaoui, M., Rziga, F. O., Mbarek, K., & Besbes, K. (2022) · Journal of Computational Electronics · doi:10.1007/s10825-022-01895-9 · Cited by 9
“3 (b) shows the I–V characteristics of the VTEAM model compared with the Ta2O5-RRAM memristor device [23].”
BackgroundMethodInfluentialSymmetric Linear Rise and Fall of Conductance in a Trilayer Stack Engineered ReRAM-Based Synapse
Vishwakarma, K., Kishore, R., & Datta, A. (2020) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.0c00585 · Cited by 7
Synapse design based on memristor
Elhamdaoui, M., Mbarek, K., Ghédira, S., Rziga, F. O., & Besbes, K. (2020) · IEEE International Conference on Design & Test of Integrated Micro & Nano-Systems (DTS) · doi:10.1109/dts48731.2020.9196061 · Cited by 7
“We explore the I-V characteristic of a Ta 2 O 5 RRAM-based memristive device which is described in [17].”
MethodKim, Y., Kim, H., Jeon, S., Kim, H. W., Hong, E., Kim, N., Choi, H., Park, H., Jeong, J., Lee, D., et al. (2024) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2024.3408784 · Cited by 8
“These attempts have resulted in high recognition accuracy [18], [19], [20], [21].”
BackgroundSelf-citationRRAM-Based Neuromorphic Computing Systems
Dananjaya, P. A., Gopalakrishnan, R., & Lew, W. S. (2021) · Springer eBooks · doi:10.1007/978-981-15-6912-8_12 · Cited by 6
A multiscale modeling approach for the simulation of OxRRAM devices
Padovani, A., Larcher, L., Woo, J., & Hwang, H. (2017) · Non-Volatile Memory Technology Symposium · doi:10.1109/nvmts.2017.8171306 · Cited by 5
“This behavior is determined by the redistribution of the applied pulse voltage along the conductive filament [37], [38].”
BackgroundSelf-citationLee, K.-J., Weng, Y.-C., Wang, L.-W., Lin, H.-N., Pal, P., Chu, S.-Y., Lu, D., & Wang, Y.-H. (2022) · Nanomaterials · doi:10.3390/nano12183252 · Cited by 6
“The hardware implemented neural systems are one of the promising alternatives for highly efficient learning and pattern recognition ability of massive information with an equivalent approach consuming low power [5].”
BackgroundElectromagnetic Analysis of Vertical Resistive Memory with a Sub-nm Thick Electrode
Alimkhanuly, B., Kim, S., Kim, L.-W., & Lee, S. (2020) · Nanomaterials · doi:10.3390/nano10091634 · Cited by 4
“In contrast, ξ in (8) is a field dependence factor which accounts for the decrease in the electric field effect after the formation of the CF due to radial diffusion of oxygen ions induced by the local temperature and Coulomb repulsion (attraction) [15,33,43].”
BackgroundInfluentialChoi, W., Ji, W., Heo, S., Lee, D., Noh, K., Lee, C., Woo, J., Kim, S., & Hwang, H. (2022) · IEEE Electron Device Letters · doi:10.1109/led.2022.3192262 · Cited by 4
Self-citationChuang, K.-C., Chung, H.-T., Chu, C.-Y., et al. (2018) · Japanese Journal of Applied Physics · doi:10.7567/jjap.57.06kc01 · Cited by 4
Hang, C.-Z., Wang, C., Gao, B., Chen, H., Xu, M., Hao, L., & Lü, H.-L. (2019) · Applied Physics Letters · doi:10.1063/1.5078782 · Cited by 5
Yan, J., Dai, L., Tang, M., Zhong, X., Song, H., Wang, J., Huang, M., & Zhong, G. (2025) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2025.3599826 · Cited by 3
“…= 0.89 and A D = 1.54) of conductance variation, attributed to its optimal STO thickness enabling weak conductive filament formation, which suppressed nonlinearity enhances synaptic weight linearity, thereby improving pattern recognition accuracy in neuromorphic computing systems [31], [32], [33].”
InfluentialProbing Traps in Ta 2 O 5 /Al 2 O 3 Memristive Switching Devices
Ranjan, A., Padovani, A., Torraca, P. L., Pan, J., Wang, W., Song, W., Bosman, M., Pey, K. L., & Raghavan, N. (2025) · ACS Applied Electronic Materials · doi:10.1021/acsaelm.5c01880 · Cited by 1
Self-citationAudio Signal-Stimulated Multilayered HfOx/TiOy Spiking Neuron Network for Neuromorphic Computing
Gao, S., Ma, M., Liang, B., Du, Y., Du, L., & Chen, K. (2024) · Nanomaterials · doi:10.3390/nano14171412 · Cited by 3
A 6.23-bit FG-based Neuromorphic Synaptic Device with Extended Input Range by Linearity Improvement
Ryu, Y.-T., & Kwon, K.-W. (2022) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic54506.2022.9748521 · Cited by 2
Memristor models for synapse component
Elhamdaoui, M., Mbarek, K., Rziga, F. O., & Besbes, K. (2021) · IEEE International Conference on Design & Test of Integrated Micro & Nano-Systems (DTS) · doi:10.1109/dts52014.2021.9497940 · Cited by 2
Design of memristor-based combinational logic circuits
Tao, Z., Wang, L., Sun, C., et al. (2024) · IEICE Electronics Express · doi:10.1587/elex.21.20230587 · Cited by 2
Effect on Resistive Switching by Inserting TiOx Thin Layer in SiOx: Ag-Based Memristor
Ilyas, N., Yuan, Y. H., Zhao, X., Li, D. Y., Jiang, X. D., & Li, W. (2020) · Materials science forum · doi:10.4028/www.scientific.net/msf.984.97 · Cited by 2
Bang, S., Oh, M.-H., Kim, M., Kim, T., Lee, D. K., Choi, Y.-J., Kim, C. S., Hong, K., Cho, S., Kim, S., et al. (2020) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic49074.2020.9051210 · Cited by 2
“Recently, resistive-switching random-access memory (RRAM), one of the most representative memristors, has been widely studied as a strong potential candidate for synaptic device towards the implementation of the neuromorphic systems owing to its great resemblance to the biological synapse, including two-terminal struc…”
BackgroundYu, A., Ma, Y., Wang, Z., Ding, X., Feng, Y., & Liu, L. (2019) · doi:10.1109/iwofc48002.2019.9078471 · Cited by 2
“In addition, RRAM devices with low-power switching characteristics are also considered as artificial electronic synapses for neuromorphic applications [2].”
BackgroundHan, C., Zhang, M., Liu, Y., Wang, X., Zhang, H., & Tong, Y. (2025) · IEEE Electron Devices Technology & Manufacturing Conference (EDTM) · doi:10.1109/edtm61175.2025.11041024 · Cited by 1
Low-dimensional silicon for neuromorphic computing
Malik, M., Wang, Y., Ni, Z., Anwar, M. A., Wang, C., Shehzad, K., Ali, A., Ali, N., Bodepudi, S. C., Pi, X., et al. (2025) · Chip · doi:10.1016/j.chip.2025.100169 · Cited by 1
The potential of semiconducting oxides in comparison to insulating oxides for memristor applications
Rudrapal, K., & Daus, A. (2026) · APL Materials · doi:10.1063/5.0314546 · Cited by 2
Multilevel Analog Switching in HfO 2 /TiO x Flexible Memristor for Precision Neuromorphic Computing
Pal, P., Singh, S., Kumar, S., Prodromakis, T., & Wang, Y. (2026) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2026.3716988 · Cited by 1
“Consequently, research e ff orts on emerging NVM (eNVM) technologies, including ferroelectric memory, phase-change memory, mag-netoresistive memory, and resistive memories (memristors), have grown dramatically in recent years [9], [10], [11], [12], [13].”
Kim, E., Jeon, S., Park, H., Jeong, J., Choi, H., Kim, Y., Kim, J. S., Lim, S., Moon, K., & Woo, J. (2025) · Neuromorphic Computing and Engineering · doi:10.1088/2634-4386/adb512 · Cited by 1
“Thus, many studies have been reported on strategies to mitigate the uniformity and reliability of the multiple states of RRAM [9, 20–23].”
Self-citationNeuromorphic applications using MOx-based memristors
Brivio, S., & Vianello, E. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-814629-3.00014-3 · Cited by 1
Woo, J.-J., Choi, J.-M., & Kwon, K.-W. (2019) · Conference proceedings · doi:10.1109/mwscas.2019.8885281
Self-citationBio-inspired Neuromorphic Computing Using Memristor Crossbar Networks
Jeong, Y. (2018) · Deep Blue (University of Michigan)
Redox-based memristive devices : towards highly scalable synaptic electronics
Dananjaya, P. A. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/146143
Spike-time dependent plasticity rule in memristor models for circuits designPreprint
Elhamdaoui, M., Rziga, F. O., Mbarek, K., & Besbes, K. (2021) · Research Square · doi:10.21203/rs.3.rs-164635/v1
Chee, M. Y. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/173840
AL2O3/ALOX Memristor with Nearly Ideal Synaptic Characteristics
He, Q., Wang, H., Bai, Y., Hu, J., Li, H., Ma, W., Xu, Y., Zhang, Y., & Yu, B. (2024) · China Semiconductor Technology International Conference (CSTIC) · doi:10.1109/cstic61820.2024.10531814
“However, there is a challenge in achieving linearity in weight updates of memristors during long-term potentiation (LTP) and long-term depression (LTD) due to the uneven formation of conductive filament over time caused by electric field [3].”
BackgroundElectric Field-Moderated Filament Control for Cryogenic RRAM Synapse
Kim, Y., & Woo, J. (2025) · IEEE Electron Device Letters · doi:10.1109/led.2025.3632969
“This result is in good agreement with the microscopic simulation results, revealing that the change in the width of the CF is related to linear current modulation [21].”
Self-citationH-Plasma Treated ZrO 2 and HfO 2 RRAM Devices for Low Power In-Memory Computing
Zeinati, A., Misra, D., Triyoso, D. H., et al. (2025) · IEEE Transactions on Materials for Electron Devices · doi:10.1109/tmat.2025.3635585
“As a result, the CF Lowers the Resistance of the RRAM device, and the Device Enters the Low Resistance States (LRS) [11], [18], [19].”
Switching Layer Design and Its Influence on RRAM Power Efficiency
Hardy, J. F., Giardini, G. S. Y., Garrard, J., et al. (2026) · Journal of Electronic Materials · doi:10.1007/s11664-026-12772-7
“19–21 In filamentary switching, CFs originate from the field-driven migration of oxygen ions or metal cations within the active layer, producing localized conductive pathways that can be repeatedly formed and ruptured.”
Lei, X., Yang, C. H., Tian, P., et al. (2026) · Applied Physics Letters · doi:10.1063/5.0321223
Ha, H., Kim, D., Kwon, O., Seo, Y., & Hwang, H. (2026) · IEEE Electron Device Letters · doi:10.1109/led.2026.3691110
“In addition, device-to-device (D2D) and cycle-to-cycle (C2C) variations should be minimized to avoid calibration overhead and inference accuracy degradation in large arrays [8].”
Self-citationModeling Endurance Degradation of VCM-based 1T1R ReRAM Cell for Circuit Simulations
Chakraborty, S., Shadmehri, S. H. H., Copetti, T., et al. (2026) · International Symposium on Quality Electronic Design (ISQED) · doi:10.1109/isqed69900.2026.11534679
“Numerous research activities have demonstrated the use of power-law characteristics in modeling various aspects of ReRAM devices, including conductive filament evolution, synaptic behavior, switching power dynamics, as well as retention and relaxation properties [2], [30]–[33].”
Metadata
- Authors
- Woo, J., Padovani, A., Moon, K., Kwak, M., Larcher, L., & Hwang, H.
- Affiliations
- Pohang University of Science and Technology (KR)
- University of Modena and Reggio Emilia (IT)
- Venue
- IEEE Electron Device Letters
- Published
- 2017-09
- Volume
- 38
- Issue
- 9
- Pages
- 1220-1223
- ISSN
- 0741-3106 (ISSN-L)
- 1558-0563
- OpenAlex
- W2737711638
- Semantic Scholar
- f5687a2171bdd95bb40c834f93b7ad2d4b770e14
- Cited by
- 103
- References
- 19
- Citations by year
- 2026: 9 · 2025: 9 · 2024: 6 · 2023: 8 · 2022: 21 · 2021: 9 · 2020: 14 · 2019: 15 · 2018: 10 · 2017: 2
- FWCI
- 4.66
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Locations
- IEEE Electron Device Letters (publishedVersion)
- IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion, cc-by)
- Open Access System for Information Sharing (Pohang University of Science and Technology) (submittedVersion)
- Funders
- MOTIE (10067794)
- KSRC Support Program for the development of the future semiconductor device
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Ferroelectric and Negative Capacitance Devices
- Physical Sciences › Materials Science › Materials Chemistry › Phase-change materials and chalcogenides
- Keywords
- resistive random access memory, conductive filaments, hafnium oxide, tantalum pentoxide, electronic synapses, neuromorphic hardware, resistive switching, oxide barrier, analog switching, multistate memory, multilayer perceptron, handwritten digit recognition, backpropagation
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.