Filters








2,019 Hits in 5.4 sec

Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping [article]

Matthias Freiberger, Peter Bienstman, Joni Dambre
2019 arXiv   pre-print
Therefore, a switch from single-reservoir computing to multi-reservoir and even deep physical reservoir computing is desirable.  ...  Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths.  ...  step (using different, randomly initialized ESNs) as a whole using backpropagation to automatically find a good task decomposition.  ... 
arXiv:1910.13332v1 fatcat:wgsv36xtozghbc6fatlrzlwile

Efficient Design of Hardware-Enabled Reservoir Computing in FPGAs [article]

Bogdan Penkovsky, Laurent Larger, Daniel Brunner
2018 arXiv   pre-print
In this work, we propose a new approach towards the efficient optimization and implementation of reservoir computing hardware reducing the required domain expert knowledge and optimization effort.  ...  We confirm the validity of those principles building reservoir computing hardware based on a field-programmable gate array.  ...  ANR-11-LABX-0001-01) and by the BiPhoProc ANR project (ANR-14-OHRI-0002-02).  ... 
arXiv:1805.03033v1 fatcat:hunx4rn3dveu7meluo5wvuolli

A Review of Designs and Applications of Echo State Networks [article]

Chenxi Sun and Moxian Song and Shenda Hong and Hongyan Li
2020 arXiv   pre-print
Since ESN was put forward in 2002, abundant existing works have promoted the progress of ESN, and the recently introduced Deep ESN model opened the way to uniting the merits of deep learning and ESNs.  ...  Recurrent Neural Networks (RNNs) have demonstrated their outstanding ability in sequence tasks and have achieved state-of-the-art in wide range of applications, such as industrial, medical, economic and  ...  Deep echo state networks With the development of deep learning [99] , Stacking architecture [100] has been introduced into reservoir computing.  ... 
arXiv:2012.02974v1 fatcat:ngp7zdv4y5cgnbnrq6ibbdmp6y

A Comprehensive Review of Deep Learning Applications in Hydrology and Water Resources [article]

Muhammed Sit, Bekir Z. Demiray, Zhongrun Xiang, Gregory J. Ewing, Yusuf Sermet, Ibrahim Demir
2020 arXiv   pre-print
Combined with the growing availability of computational resources and popularity of deep learning, these data are transformed into actionable and practical knowledge, revolutionizing the water industry  ...  The study provides a comprehensive review of state-of-the-art deep learning approaches used in the water industry for generation, prediction, enhancement, and classification tasks, and serves as a guide  ...  Toward this end, many researchers have applied cutting-edge deep learning architectures to the runoff prediction and flood forecasting tasks.  ... 
arXiv:2007.12269v1 fatcat:7vc2r76fozhtpcveli6h4uldie

Role of non-linear data processing on speech recognition task in the framework of reservoir computing [article]

Flavio Abreu Araujo, Mathieu Riou, Jacob Torrejon, Sumito Tsunegi, Damien Querlioz, Kay Yakushiji, Akio Fukushima, Hitoshi Kubota, Shinji Yuasa, Mark D. Stiles, Julie Grollier
2019 arXiv   pre-print
One of the preferred tasks for bench-marking such devices is automatic speech recognition.  ...  The reservoir computing neural network architecture is widely used to test hardware systems for neuromorphic computing.  ...  Rather than a set of N θ physical neurons, our reservoir consists of a single physical neuron evaluated at N θ periodic times.  ... 
arXiv:1906.02812v3 fatcat:dvvh4pr26zfq5dqu7fd7ozgzpe

A new method for extracting knowledge from patents to inspire designers during the problem-solving phase

Ulises Yosafat Valverde, Jean-Pierre Nadeau, Dominique Scaravetti
2017 Journal of engineering design  
Many different approaches are more oriented towards the automation of complex tasks, such as analysis and knowledge extraction through computer science and artificial intelligence techniques.  ...  All of the developed modules have an automatic part to facilitate the task, but the analysis of patents, the identification of pertinent keywords, and the functional decomposition must be done manually  ... 
doi:10.1080/09544828.2017.1316361 fatcat:wd7iwjlgmzaathrxxnlhe3qvde

Artificial-Intelligence-Driven Customized Manufacturing Factory: Key Technologies, Applications, and Challenges

Jiafu Wan, Xiaomin Li, Hong-Ning Dai, Andrew Kusiak, Miguel Martinez-Garcia, Di Li
2020 Proceedings of the IEEE  
., machine learning, multi-agent systems, Internet of Things, big data, and cloud-edge computing are surveyed.  ...  The traditional production paradigm of large batch production does not offer flexibility towards satisfying the requirements of individual customers.  ...  The mechanism of self-organizing schedules for multiple production tasks can be divided into three steps: task analysis, task decomposition, and task execution.  ... 
doi:10.1109/jproc.2020.3034808 fatcat:bpljlzguqjhypedblczhmch2uq

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically  ...  This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors.  ...  This new class of extremely low-power and lowlatency artificial intelligence systems could, In a world where power-hungry deep learning techniques are becoming a commodity, and at the same time, environmental  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

Data-driven geophysics: from dictionary learning to deep learning [article]

Siwei Yu, Jianwei Ma
2020 arXiv   pre-print
Understanding the principles of geophysical phenomena is an essential and challenging task.  ...  We present a coding tutorial and a summary of tips for beginners and interested geophysical readers to rapidly explore deep learning.  ...  Acknowledgments The work was supported in part by the National Key Research and Development Program Data Availability Statement Data were not used, nor created for this research.  ... 
arXiv:2007.06183v2 fatcat:ow45ejo7izbkpmssedwd74rbym

Leveraging AI in Photonics and Beyond

Gandhi Alagappan, Jun Rong Ong, Zaifeng Yang, Thomas Yong Long Ang, Weijiang Zhao, Yang Jiang, Wenzu Zhang, Ching Eng Png
2022 Photonics  
This article reviews leveraging AI in photonics modeling, simulation, and inverse design; leveraging photonics computing for implementing AI algorithms; and leveraging AI beyond photonics topics, such  ...  Photonics benefit a great deal from AI, and AI, in turn, benefits from photonics by carrying out AI algorithms, such as complicated deep neural networks using photonics components that use photons rather  ...  Reservoir Computing Reservoir computing is a framework that is closely related to recurrent neural networks.  ... 
doi:10.3390/photonics9020075 fatcat:pkomp66omrg6hc7ydm7byetjua

Model-Based Design and Formal Verification Processes for Automated Waterway System Operations

Leonard Petnga, Mark Austin
2016 Systems  
In a step toward overcoming these challenges, this paper argues that programs for waterway and canal modernization and sustainability can benefit significantly from system thinking, supported by systems  ...  Failures, delays, incidents and accidents in aging waterway systems are doing little to attract the technical and economic assistance required for modernization and sustainability.  ...  Inputs and outputs: Ships are physical entities that enter and exit the waterway through the above-mentioned boundaries.  ... 
doi:10.3390/systems4020023 fatcat:krzvtb25ezhntgtteq7nez6ug4

Sample-level sound synthesis with recurrent neural networks and conceptors

Chris Kiefer
2019 PeerJ Computer Science  
Conceptors are a recent development in the field of reservoir computing; they can be used to influence the dynamics of recurrent neural networks (RNNs), enabling generation of arbitrary patterns based  ...  Limitations of conceptor models are revealed with regards to reproduction quality, and pragmatic limitations are also shown, where rises in computation and memory requirements preclude the use of these  ...  ACKNOWLEDGEMENTS Thank you to Sussex Humanities Lab for generous access of their computing facilities. ADDITIONAL INFORMATION AND DECLARATIONS Funding The author received no funding for this work.  ... 
doi:10.7717/peerj-cs.205 pmid:33816858 pmcid:PMC7924416 fatcat:fo4rmbabdjfafapjkeajnpmdpu

Efficient high-dimensional variational data assimilation with machine-learned reduced-order models [article]

Romit Maulik, Vishwas Rao, Jiali Wang, Gianmarco Mengaldo, Emil Constantinescu, Bethany Lusch, Prasanna Balaprakash, Ian Foster, Rao Kotamarthi
2021 arXiv   pre-print
high-performance computer.  ...  Consequently, gradients of our DA objective function with respect to the decision variables are obtained rapidly via automatic differentiation.  ...  Morever, in contrast with [41] where a reservoir computer was used as the surrogate, our ML emulator is given by deep recurrent neural network (i.e., a long shortterm memory neural network with several  ... 
arXiv:2112.07856v1 fatcat:w5zyadkiwvgunbjvwcrpwkx5wq

Table of Contents

2020 2020 IEEE Symposium Series on Computational Intelligence (SSCI)  
Olbricht .......... 513 Towards a Data-Driven Fuzzy-Geospatial Pandemic Modelling Amir Pourabdollah and Ahmad Lotfi .......... 521 Who is physically active?  ...  1710 Towards Potential of N-back Task as Protocol and EEGNet for the EEG-based Biometric Nima Salimi, Michael Barlow and Erandi Lakshika .......... 1718 Efficient Method for High-Resolution Fingerprint  ... 
doi:10.1109/ssci47803.2020.9308155 fatcat:hyargfnk4vevpnooatlovxm4li

Evidence from three-dimensional seismic tomography for a substantial accumulation of gas hydrate in a fluid-escape chimney in the Nyegga pockmark field, offshore Norway

Andreia Plaza-Faverola, Graham K. Westbrook, Stephan Ker, Russell J. K. Exley, Audrey Gailler, Tim A. Minshull, Karine Broto
2010 Journal of Geophysical Research  
Single channel seismic, ocean bottom seismic recorders (OBS), 3D high resolution P-Cable seismic and bathymetry data of the study area were acquired during cruises in July 2006 and 2008 on board R/V Jan  ...  Ocean bottom seismic recorders (OBSs) were kindly provided by UK Ocean Bottom Instrumentation Consortium and by IFREMER.  ...  Many of them shared with family, friends and colleagues, and as such they are reviewed in the following acknowledgements.  ... 
doi:10.1029/2009jb007078 fatcat:j3truqv6tbhk5bilabicttnfce
« Previous Showing results 1 — 15 out of 2,019 results