1
|
Choi S, Shin J, Park G, Eo JS, Jang J, Yang JJ, Wang G. 3D-integrated multilayered physical reservoir array for learning and forecasting time-series information. Nat Commun 2024; 15:2044. [PMID: 38448419 PMCID: PMC10917743 DOI: 10.1038/s41467-024-46323-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Accepted: 02/22/2024] [Indexed: 03/08/2024] Open
Abstract
A wide reservoir computing system is an advanced architecture composed of multiple reservoir layers in parallel, which enables more complex and diverse internal dynamics for multiple time-series information processing. However, its hardware implementation has not yet been realized due to the lack of a high-performance physical reservoir and the complexity of fabricating multiple stacks. Here, we achieve a proof-of-principle demonstration of such hardware made of a multilayered three-dimensional stacked 3 × 10 × 10 tungsten oxide memristive crossbar array, with which we further realize a wide physical reservoir computing for efficient learning and forecasting of multiple time-series data. Because a three-layer structure allows the seamless and effective extraction of intricate three-dimensional local features produced by various temporal inputs, it can readily outperform two-dimensional based approaches extensively studied previously. Our demonstration paves the way for wide physical reservoir computing systems capable of efficiently processing multiple dynamic time-series information.
Collapse
Affiliation(s)
- Sanghyeon Choi
- KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea
- Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, 90089, USA
- Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, 93106, USA
| | - Jaeho Shin
- KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea
- Department of Chemistry, Rice University, 6100 Main Street, Houston, TX, 77005, USA
| | - Gwanyeong Park
- KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea
| | - Jung Sun Eo
- KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea
| | - Jingon Jang
- KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea
- School of Computer and Information Engineering, Kwangwoon University, 20 Kwangwoon-ro, Nowon-gu, Seoul, 01897, Republic of Korea
| | - J Joshua Yang
- Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, 90089, USA.
| | - Gunuk Wang
- KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea.
- Department of Integrative Energy Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea.
- Center for Neuromorphic Engineering, Korea Institute of Science and Technology, Seoul, 02792, Republic of Korea.
| |
Collapse
|
2
|
Jeon J, Kim P, Jang B, Kim Y. PDE-guided reservoir computing for image denoising with small data. CHAOS (WOODBURY, N.Y.) 2021; 31:073103. [PMID: 34340316 DOI: 10.1063/5.0049911] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/10/2021] [Accepted: 06/16/2021] [Indexed: 06/13/2023]
Abstract
While network-based techniques have shown outstanding performance in image denoising in the big data regime requiring massive datasets and expensive computation, mathematical understanding of their working principles is very limited. Not to mention, their relevance to traditional mathematical approaches has not attracted much attention. Therefore, we suggest how reservoir computing networks can be strengthened in combination with conventional partial differential equation (PDE) methods for image denoising, especially in the small data regime. Given image data, PDEs generate sequential datasets enhancing desired image features, which provide the network with a better guideline for training in reservoir computing. The proposed procedure, reservoir computing in collaboration with PDEs (RCPDE), offers a synergetic combination of data-driven network-based methods and mathematically well-established PDE methods. It turns out that RCPDE outperforms both the usual reservoir computing and existing PDE approaches in image denoising. Furthermore, RCPDE also excels deep neural networks such as a convolutional neural network both in quality and in time in the small data regime. We believe that RCPDE reveals the great potential of reservoir computing in collaboration with various mathematically justifiable dynamics for better performance as well as for better mathematical understanding.
Collapse
Affiliation(s)
- Jongha Jeon
- BigData & AI Lab, Hana Institute of Technology (HIT)-Hana TI, Seoul 06133, South Korea
| | - Pilwon Kim
- Department of Mathematical Sciences, Ulsan National Institute of Science and Technology (UNIST), Ulsan Metropolitan City 44919, South Korea
| | - Bongsoo Jang
- Department of Mathematical Sciences, Ulsan National Institute of Science and Technology (UNIST), Ulsan Metropolitan City 44919, South Korea
| | - Yunho Kim
- Department of Mathematical Sciences, Ulsan National Institute of Science and Technology (UNIST), Ulsan Metropolitan City 44919, South Korea
| |
Collapse
|
3
|
Hadaeghi F, Diercks BP, Schetelig D, Damicelli F, Wolf IMA, Werner R. Spatio-temporal feature learning with reservoir computing for T-cell segmentation in live-cell [Formula: see text] fluorescence microscopy. Sci Rep 2021; 11:8233. [PMID: 33859269 PMCID: PMC8050068 DOI: 10.1038/s41598-021-87607-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2020] [Accepted: 03/25/2021] [Indexed: 11/09/2022] Open
Abstract
Advances in high-resolution live-cell [Formula: see text] imaging enabled subcellular localization of early [Formula: see text] signaling events in T-cells and paved the way to investigate the interplay between receptors and potential target channels in [Formula: see text] release events. The huge amount of acquired data requires efficient, ideally automated image processing pipelines, with cell localization/segmentation as central tasks. Automated segmentation in live-cell cytosolic [Formula: see text] imaging data is, however, challenging due to temporal image intensity fluctuations, low signal-to-noise ratio, and photo-bleaching. Here, we propose a reservoir computing (RC) framework for efficient and temporally consistent segmentation. Experiments were conducted with Jurkat T-cells and anti-CD3 coated beads used for T-cell activation. We compared the RC performance with a standard U-Net and a convolutional long short-term memory (LSTM) model. The RC-based models (1) perform on par in terms of segmentation accuracy with the deep learning models for cell-only segmentation, but show improved temporal segmentation consistency compared to the U-Net; (2) outperform the U-Net for two-emission wavelengths image segmentation and differentiation of T-cells and beads; and (3) perform on par with the convolutional LSTM for single-emission wavelength T-cell/bead segmentation and differentiation. In turn, RC models contain only a fraction of the parameters of the baseline models and reduce the training time considerably.
Collapse
Affiliation(s)
- Fatemeh Hadaeghi
- Department of Computational Neuroscience, Center for Experimental Medicine, University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
| | - Björn-Philipp Diercks
- Department of Biochemistry and Molecular Cell Biology, Center for Experimental Medicine, University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
| | - Daniel Schetelig
- Department of Computational Neuroscience, Center for Experimental Medicine, University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
- Center for Biomedical Artificial Intelligence (bAIome), University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
| | - Fabrizio Damicelli
- Department of Computational Neuroscience, Center for Experimental Medicine, University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
| | - Insa M. A. Wolf
- Department of Biochemistry and Molecular Cell Biology, Center for Experimental Medicine, University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
| | - René Werner
- Department of Computational Neuroscience, Center for Experimental Medicine, University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
- Center for Biomedical Artificial Intelligence (bAIome), University Medical Center Hamburg-Eppendorf (UKE), Martinistrasse 52, 20246 Hamburg, Germany
| |
Collapse
|