Yunpeng Guo: Department of Precision Instrument, Center for Brain Inspired Computing Research, Tsinghua University, Beijing, 100084, China.
Wenrui Duan: School of Instrument Science and Opto Electronics Engineering, Laboratory of Intelligent Microsystems, Beijing Information Science & Technology University, Beijing, 100101, China. duanwr10@buaa.edu.cn. ORCID
Xue Liu: Department of Precision Instrument, Center for Brain Inspired Computing Research, Tsinghua University, Beijing, 100084, China. liuqingxue@mail.tsinghua.edu.cn.
Xinxin Wang: Department of Precision Instrument, Center for Brain Inspired Computing Research, Tsinghua University, Beijing, 100084, China.
Lidan Wang: School of Artificial Intelligence, Southwest University, Chongqing, 400715, China. ORCID
Shukai Duan: School of Artificial Intelligence, Southwest University, Chongqing, 400715, China. ORCID
Cheng Ma: Department of Precision Instrument, Center for Brain Inspired Computing Research, Tsinghua University, Beijing, 100084, China. macheng@tsinghua.edu.cn. ORCID
Huanglong Li: Department of Precision Instrument, Center for Brain Inspired Computing Research, Tsinghua University, Beijing, 100084, China. li_huanglong@mail.tsinghua.edu.cn. ORCID
Artificial neural networks (ANNs) have gained considerable momentum in the past decade. Although at first the main task of the ANN paradigm was to tune the connection weights in fixed-architecture networks, there has recently been growing interest in evolving network architectures toward the goal of creating artificial general intelligence. Lagging behind this trend, current ANN hardware struggles for a balance between flexibility and efficiency but cannot achieve both. Here, we report on a novel approach for the on-demand generation of complex networks within a single memristor where multiple virtual nodes are created by time multiplexing and the non-trivial topological features, such as small-worldness, are generated by exploiting device dynamics with intrinsic cycle-to-cycle variability. When used for reservoir computing, memristive complex networks can achieve a noticeable increase in memory capacity a and respectable performance boost compared to conventional reservoirs trivially implemented as fully connected networks. This work expands the functionality of memristors for ANN computing.
References
Krizhevsky, A., Ilya, S. & Geoffrey, E. H. Imagenet classification with deep convolutional neural networks. Adv. neural Inf. Process. Syst. 25, 1097–1105 (2012).
He, K., Zhang, X., Ren, S. & Sun, J. in Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778 (IEEE, 2016).
Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2261–2269 (2017).
Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 6000–6010 (2017).
Stanley, K. O., Clune, J., Lehman, J. & Miikkulainen, R. Designing neural networks through neuroevolution. Nat. Mach. Intell. 1, 24–35 (2019).
Elsken, T., Metzen, J. H. & Hutter, F. Neural architecture search: A survey. J. Mach. Learn. Res. 20, 1997–2017 (2019).
Sporns, O. The non-random brain: efficiency, economy, and complex dynamics. Front. Comput. Neurosci. 5, 5 (2011).
[PMID: 21369354]
Mead, C. Neuromorphic electronic systems. Proc. IEEE 78, 1629–1636 (1990).
Xia, Q. & Yang, J. J. Memristive crossbar arrays for brain-inspired computing. Nat. Mater. 18, 309–323 (2019).
[PMID: 30894760]
Yao, P. et al. Fully hardware-implemented memristor convolutional neural network. Nature 577, 641–646 (2020).
[PMID: 31996818]
Li, C. et al. Long short-term memory networks in memristor crossbar arrays. Nat. Mach. Intell. 1, 49–57 (2019).
Wang, Z. et al. Reinforcement learning with analogue memristor arrays. Nat. Electron. 2, 115–124 (2019).
Wang, Z. et al. In situ training of feed-forward and recurrent convolutional memristor networks. Nat. Mach. Intell. 1, 434–442 (2019).
Huo, Q. et al. A computing-in-memory macro based on three-dimensional resistive random-access memory. Nat. Electron. 5, 469–477 (2022).
Kim, H., Mahmoodi, M., Nili, H. & Strukov, D. B. 4K-memristor analog-grade passive crossbar circuit. Nat. Commun. 12, 5198 (2021).
[PMID: 34465783]
Le Gallo, M. et al. A 64-core mixed-signal in-memory compute chip based on phase-change memory for deep neural network inference. Nat. Electron. 2, 1–14 (2023).
Gao, B. et al. Concealable physically unclonable function chip with a memristor array. Sci. Adv. 8, 7753 (2022).
Zhang, Z. et al. Truly concomitant and independently expressed short‐and long‐term plasticity in a Bi2O2Se‐based three‐terminal memristor. Adv. Mater. 31, 1805769 (2019).
Dalgaty, T. et al. In situ learning using intrinsic memristor variability via Markov chain Monte Carlo sampling. Nat. Electron. 4, 151–161 (2021).
Wang, W. et al. Integration and co-design of memristive devices and algorithms for artificial intelligence. Iscience 23, 101809 (2020).
[PMID: 33305176]
Kumar, S., Wang, X., Strachan, J. P., Yang, Y. & Lu, W. D. Dynamical memristors for higher-complexity neuromorphic computing. Nat. Rev. Mater. 7, 575–591 (2022).
Jiang, H. et al. A provable key destruction scheme based on memristive crossbar arrays. Nat. Electron. 1, 548–554 (2018).
Nili, H. et al. Hardware-intrinsic security primitives enabled by analogue state and nonlinear conductance variations in integrated memristors. Nat. Electron. 1, 197–202 (2018).
Jiang, H. et al. A novel true random number generator based on a stochastic diffusive memristor. Nat. Commun. 8, 1–9 (2017).
Kim, G. et al. Self-clocking fast and variation tolerant true random number generator based on a stochastic mott memristor. Nat. Commun. 12, 1–8 (2021).
Dutta, S. et al. Neural sampling machine with stochastic synapse allows brain-like learning and inference. Nat. Commun. 13, 1–10 (2022).
Cai, F. et al. Power-efficient combinatorial optimization using intrinsic noise in memristor Hopfield neural networks. Nat. Electron. 3, 409–418 (2020).
Mahmoodi, M., Prezioso, M. & Strukov, D. Versatile stochastic dot product circuits based on nonvolatile memories for high performance neurocomputing and neurooptimization. Nat. Commun. 10, 1–10 (2019).
Kumar, S., Strachan, J. P. & Williams, R. S. Chaotic dynamics in nanoscale NbO2 Mott memristors for analogue computing. Nature 548, 318–321 (2017).
[PMID: 28792931]
Tuma, T., Pantazi, A., Le Gallo, M., Sebastian, A. & Eleftheriou, E. Stochastic phase-change neurons. Nat. Nanotechnol. 11, 693–699 (2016).
[PMID: 27183057]
Wang, S. et al. Echo state graph neural networks with analogue random resistive memory arrays. Nat. Mach. Intell. 5, 104–113 (2023).
Mao, R. et al. Experimentally validated memristive memory augmented neural network with efficient hashing and similarity search. Nat. Commun. 13, 6284 (2022).
[PMID: 36271072]
Yi, W. et al. Biological plausibility and stochasticity in scalable VO2 active memristor neurons. Nat. Commun. 9, 4661 (2018).
[PMID: 30405124]
Zhang, X. et al. An artificial spiking afferent nerve based on Mott memristors for neurorobotics. Nat. Commun. 11, 51 (2020).
[PMID: 31896758]
Yoon, J. H. et al. An artificial nociceptor based on a diffusive memristor. Nat. Commun. 9, 417 (2018).
[PMID: 29379008]
Duan, Q. et al. Spiking neurons with spatiotemporal dynamics and gain modulation for monolithically integrated memristive neural networks. Nat. Commun. 11, 3399 (2020).
[PMID: 32636385]
Yuan, R. et al. A calibratable sensory neuron based on epitaxial VO2 for spike-based neuromorphic multisensory system. Nat. Commun. 13, 3973 (2022).
[PMID: 35803938]
Lin, Y. et al. Uncertainty quantification via a memristor Bayesian deep neural network for risk-sensitive reinforcement learning. Nat. Mach. Intelligence. 5, 714–723 (2023).
Zheng, Y. et al. Hardware implementation of Bayesian network based on two-dimensional memtransistors. Nat. Commun. 13, 5578 (2022).
[PMID: 36151079]
Appeltant, L. et al. Information processing using a single dynamical node as complex system. Nat. Commun. 2, 1–6 (2011).
Tanaka, G. et al. Recent advances in physical reservoir computing: a review. Neural Netw. 115, 100–123 (2019).
[PMID: 30981085]
Du, C. et al. Reservoir computing using dynamic memristors for temporal information processing. Nat. Commun. 8, 1–10 (2017).
Moon, J. et al. Temporal data classification and forecasting using a memristor-based reservoir computing system. Nat. Electron. 2, 480–487 (2019).
Liu, K. et al. An optoelectronic synapse based on α-In2Se3 with controllable temporal dynamics for multimode and multiscale reservoir computing. Nat. Electron. 5, 761–773 (2022).
Zhu, X., Wang, Q. & Lu, W. D. Memristor networks for real-time neural activity analysis. Nat. Commun. 11, 2439 (2020).
[PMID: 32415218]
Liu, K. et al. Multilayer reservoir computing based on ferroelectric α-in2se3 for hierarchical information processing. Adv. Mater. 34, 2108826 (2022).
Chen, Z. et al. All-ferroelectric implementation of reservoir computing. Nat. Commun. 14, 3585 (2023).
[PMID: 37328514]
Sillin, H. O. et al. A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing. Nanotechnology 24, 384004 (2013).
[PMID: 23999129]
Milano, G. et al. In materia reservoir computing with a fully memristive architecture based on self-organizing nanowire networks. Nat. Mater. 21, 195–202 (2022).
[PMID: 34608285]
Wu, W. et al. Improving analog switching in HfO x-based resistive memory with a thermal enhanced layer. IEEE Electron Device Lett. 38, 1019–1022 (2017).
Wang, Z. et al. Memristors with diffusive dynamics as synaptic emulators for neuromorphic computing. Nat. Mater. 16, 101–108 (2017).
[PMID: 27669052]
Brunner, D., Soriano, M. C., Mirasso, C. R. & Fischer, I. Parallel photonic information processing at gigabyte per second data rates using transient states. Nat. Commun. 4, 1364 (2013).
[PMID: 23322052]
Larger, L. et al. High-speed photonic reservoir computing using a time-delay-based architecture: Million words per second classification. Phys. Rev. X 7, 011015 (2017).
Menzel, S., Von Witzleben, M., Havel, V. & Böttger, U. The ultimate switching speed limit of redox-based resistive switching devices. Faraday Discuss. 213, 197–213 (2019).
[PMID: 30357198]
Stelzer, F., Röhm, A., Vicente, R., Fischer, I. & Yanchuk, S. Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops. Nat. Commun. 12, 1–10 (2021).
Watts, D. J. & Strogatz, S. H. Collective dynamics of ‘small-world’networks. nature 393, 440–442 (1998).
[PMID: 9623998]
Song, H. F. & Wang, X.-J. Simple, distance-dependent formulation of the Watts-Strogatz model for directed and undirected small-world networks. Phys. Rev. E 90, 062801 (2014).
Buzsáki, G., Geisler, C., Henze, D. A. & Wang, X.-J. Interneuron diversity series: circuit complexity and axon wiring economy of cortical interneurons. Trends Neurosci. 27, 186–193 (2004).
[PMID: 15046877]
Erdős, P. & Rényi, A. On the evolution of random graphs. Publ. Math. Inst. Hung. Acad. Sci. 5, 17–60 (1960).
Barabási, A.-L. & Albert, R. Emergence of scaling in random networks. Science 286, 509–512 (1999).
[PMID: 10521342]
Lukoševičius, M. & Jaeger, H. Reservoir computing approaches to recurrent neural network training. Computer Sci. Rev. 3, 127–149 (2009).
Zou, X.-L., Huang, T.-J. & Wu, S. Towards a new paradigm for brain-inspired computer vision. Machine Intelligence Research 19, 412–424 (2022).
Jaeger, H. The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. Bonn., Ger.: Ger. Natl Res. Cent. Inf. Technol. GMD Tech. Rep. 148, 13 (2001).
Zhong, Y. et al. Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing. Nat. Commun. 12, 408 (2021).
[PMID: 33462233]
Hart, J. D., Schmadel, D. C., Murphy, T. E. & Roy, R. Experiments with arbitrary networks in time-multiplexed delay systems. Chaos 27, 121103 (2017).
Stelzer, F. & Yanchuk, S. Emulating complex networks with a single delay differential equation. Eur. Phys. J. Spec. Top. 230, 2865–2874 (2021).
Zhong, Y. et al. A memristor-based analogue reservoir computing system for real-time and power-efficient signal processing. Nat. Electron. 5, 672–681 (2022).
Kawai, Y., Park, J. & Asada, M. A small-world topology enhances the echo state property and signal propagation in reservoir computing. Neural Netw. 112, 15–23 (2019).
[PMID: 30735913]
Jaeger, H. & Haas, H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304, 78–80 (2004).
[PMID: 15064413]
Grants
61974082/National Natural Science Foundation of China (National Science Foundation of China)
