Results 51 to 60 of about 139,178 (278)

Evolutionary aspects of reservoir computing [PDF]

Philosophical Transactions of the Royal Society B: Biological Sciences, 2019
Reservoir computing (RC) is a powerful computational paradigm that allows high versatility with cheap learning. While other artificial intelligence approaches need exhaustive resources to specify their inner workings, RC is based on a reservoir with highly nonlinear dynamics that does not require a fine tuning of its parts. These dynamics project input
openaire   +4 more sources

Enhancing the performance of quantum reservoir computing and solving the time-complexity problem by artificial memory restriction

Physical Review Research
We propose a scheme that can enhance the performance and reduce the computational cost of quantum reservoir computing. Quantum reservoir computing is a computing approach which aims at utilizing the complexity and high dimensionality of small quantum ...
Saud Čindrak, Brecht Donvil, Kathy Lüdge, Lina Jaurigue   +3 more
doaj   +1 more source

Experimental Demonstration of High‐Performance Physical Reservoir Computing with Nonlinear Interfered Spin Wave Multidetection

Advanced Intelligent Systems, 2023
Physical reservoir computing, which is a promising method for the implementation of highly efficient artificial intelligence devices, requires a physical system with nonlinearity, fading memory, and the ability to map in high dimensions.
Wataru Namiki, Daiki Nishioka, Yu Yamaguchi, Takashi Tsuchiya, Tohru Higuchi, Kazuya Terabe   +5 more
doaj   +1 more source

A Comparative Study of Reservoir Computing for Temporal Signal Processing [PDF]

, 2014
Reservoir computing (RC) is a novel approach to time series prediction using recurrent neural networks. In RC, an input signal perturbs the intrinsic dynamics of a medium called a reservoir.
Banda, Peter, Goudarzi, Alireza, Lakin, Matthew R., Stefanovic, Darko, Teuscher, Christof   +4 more
core   +2 more sources

Hierarchical Temporal Representation in Linear Reservoir Computing

, 2017
Recently, studies on deep Reservoir Computing (RC) highlighted the role of layering in deep recurrent neural networks (RNNs). In this paper, the use of linear recurrent units allows us to bring more evidence on the intrinsic hierarchical temporal ...
Claudio Gallicchio, Claudio Gallicchio, D Koryakin, D Verstraeten, G Holzmann, H Jaeger, H Jaeger, J Schmidhuber, J Schmidhuber, M Lukoševičius, M Čerňanskỳ, S Otte, Y Xue   +12 more
core   +1 more source

A methionine‐lined active site governs carbocation stabilization and product specificity in a bacterial terpene synthase

FEBS Letters, EarlyView.
This study reveals a unique active site enriched in methionine residues and demonstrates that these residues play a critical role by stabilizing carbocation intermediates through novel sulfur–cation interactions. Structure‐guided mutagenesis further revealed variants with significantly altered product profiles, enhancing pseudopterosin formation. These
Marion Ringel, Carl P. O. Helmer, Shani Zev, Ronja Driller, Emily Buhr, Markus Reinbold, Renana Schwartz, Gabriel Foley, Mikael Boden, Daniel Garbe, Gerhard Schenk, Dan Thomas Major, Bernhard Loll, Thomas Brück   +13 more
wiley   +1 more source

Infinite-Dimensional Reservoir Computing

Neural Networks
Reservoir computing approximation and generalization bounds are proved for a new concept class of input/output systems that extends the so-called generalized Barron functionals to a dynamic context. This new class is characterized by the readouts with a certain integral representation built on infinite-dimensional state-space systems.
Lukas Gonon, Lyudmila Grigoryeva, Juan-Pablo Ortega   +2 more
openaire   +5 more sources

Towards mixed physical node reservoir computing: light-emitting synaptic reservoir system with dual photoelectric output

Light: Science & Applications
Memristor-based physical reservoir computing holds significant potential for efficiently processing complex spatiotemporal data, which is crucial for advancing artificial intelligence.
Minrui Lian, Changsong Gao, Zhenyuan Lin, Liuting Shan, Cong Chen, Yi Zou, Enping Cheng, Changfei Liu, Tailiang Guo, Wei Chen, Huipeng Chen   +10 more
doaj   +1 more source

In vitro models of cancer‐associated fibroblast heterogeneity uncover subtype‐specific effects of CRISPR perturbations

Molecular Oncology, EarlyView.
Development of therapies targeting cancer‐associated fibroblasts (CAFs) necessitates preclinical model systems that faithfully represent CAF–tumor biology. We established an in vitro coculture system of patient‐derived pancreatic CAFs and tumor cell lines and demonstrated its recapitulation of primary CAF–tumor biology with single‐cell transcriptomics ...
Elysia Saputra, Shamsudheen Karuthedath Vellarikkal, Lixia Li, Hong Sun, Khoa Nguyen, Amber Montano, Suchitra Natarajan, Federica Piccioni, Alex Michael Tamburino, Xin Yu, Aleksandra Katarzyna Olow   +10 more
wiley   +1 more source

Reservoir Computing Approach to Robust Computation using Unreliable Nanoscale Networks

, 2014
As we approach the physical limits of CMOS technology, advances in materials science and nanotechnology are making available a variety of unconventional computing substrates that can potentially replace top-down-designed silicon-based computing devices ...
A. Atiya, A. Rodan, A.Z. Stieg, D. Verstraeten, F. Wyffels, G. Snider, H. Jaeger, H.O. Sillin, J.W. Lawson, K. Terabe, L. Žaloudek, M. Haselman, M. Hermans, M. Lukoševičius, M. Lukoševičius, M.C. Ozturk, P. Erdös, P. Xu, R. Penrose, S. Dasgupta, S. Sarangi, W. Maass, Y. Chen   +22 more
core   +1 more source