更改

储备池计算 (查看源代码)

2022年6月6日 (一) 15:49的版本

添加669字节、 2022年6月6日 (一) 15:49

无编辑摘要

第73行：第73行：

==== Context reverberation network ====

−

An early example of reservoir computing was the context reverberation network.<ref>

+

An early example of reservoir computing was the context reverberation network.<ref name=":14">

[[Kevin Kirby|Kirby, Kevin]]. "Context dynamics in neural sequential learning."

Proceedings of the Florida Artificial Intelligence Research Symposium FLAIRS (1991), 66–70.

第87行：第87行：

上下文混响网络

−

上下文混响网络是储备池计算的一个早期实例。在这种结构中，一个输入层将信号输入到一个高维动力系统中，这个高维动力系统中的信息由一个可训练的单层感知器读出。有两种类型的动力学系统: 其中一种是将随机权重固定的递归神经网络，另一种动力学系统是受 Alan Turing 的形态发生模型启发的连续反应扩散系统。在可训练层，感知器将当前输入与在动力学系统中回响的信号联系起来，这个在动力学系统中回响的信号被认为是为输入提供的一个动力学的“上下文”。用后来的工作的术语来讲，反应扩散系统就相当于储备池库。

+

上下文混响网络是储备池计算的一个早期实例。<ref name=":14" />在这种结构中，一个输入层将信号输入到一个高维动力系统中，这个高维动力系统中的信息由一个可训练的单层感知器读出。有两种类型的动力学系统: 其中一种是将随机权重固定的递归神经网络，另一种动力学系统是受 Alan Turing 的形态发生模型启发的连续反应扩散系统。在可训练层，感知器将当前输入与在动力学系统中回响的信号联系起来，这个在动力学系统中回响的信号被认为是为输入提供的一个动力学的“上下文”。用后来的工作的术语来讲，反应扩散系统就相当于储备池库。

==== Echo state network ====

−

{{main|Echo state network}}The Tree Echo State Network (TreeESN) model represents a generalization of the reservoir computing framework to tree structured data.<ref>{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|year=2013|title=Tree Echo State Networks|journal=Neurocomputing|volume=101|pages=319–337|doi=10.1016/j.neucom.2012.08.017|hdl=11568/158480|hdl-access=free}}</ref>

+

{{main|Echo state network}}The Tree Echo State Network (TreeESN) model represents a generalization of the reservoir computing framework to tree structured data.<ref name=":15">{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|year=2013|title=Tree Echo State Networks|journal=Neurocomputing|volume=101|pages=319–337|doi=10.1016/j.neucom.2012.08.017|hdl=11568/158480|hdl-access=free}}</ref>

The Tree Echo State Network (TreeESN) model represents a generalization of the reservoir computing framework to tree structured data.

第96行：第96行：

回声状态网络

−

树状回声状态网络(TreeESN)模型代表了储备池计算框架向树状结构数据的推广。

+

树状回声状态网络(TreeESN)模型代表了储备池计算框架向树状结构数据的推广。<ref name=":15" />

==== Liquid-state machine ====

第111行：第111行：

The liquid (i.e. reservoir) of a Chaotic Liquid State Machine (CLSM), or chaotic reservoir, is made from chaotic spiking neurons but which stabilize their activity by settling to a single hypothesis that describes the trained inputs of the machine. This is in contrast to general types of reservoirs that don’t stabilize. The liquid stabilization occurs via synaptic plasticity and chaos control that govern neural connections inside the liquid. CLSM showed promising results in learning sensitive time series data.

−

一个混沌液体状态机(CLSM)中的液态(比如储备池)或者混沌储备池，是由混沌脉冲神经元构成，但它们通过确立一个描述机器的被训练的输入的单一假设来稳定其活动。这与通常不稳定类型的储备池形成了鲜明的对比。液态稳定化是通过突触可塑性以及管理着液态内部的神经连接的混沌控制来实现的。CLSM 在学习敏感时间序列数据方面取得了良好的效果。

+

一个混沌液体状态机(CLSM)中的液态(比如储备池)或者混沌储备池<ref name=":7" /><ref name=":8" />，是由混沌脉冲神经元构成，但它们通过确立一个描述机器的被训练的输入的单一假设来稳定其活动。这与通常不稳定类型的储备池形成了鲜明的对比。液态稳定化是通过突触可塑性以及管理着液态内部的神经连接的混沌控制来实现的。CLSM 在学习敏感时间序列数据方面取得了良好的效果。<ref name=":7" /><ref name=":8" />

==== Nonlinear transient computation ====

第120行：第120行：

非线性瞬态计算

−

当依赖时间的输入信号从这种储备池机制的内部动态性分离开来时，信息处理是最有效的。这些偏离引起瞬态或暂时的变化，这些变化在设备的输出中得到了体现。

+

当依赖时间的输入信号从这种储备池机制的内部动态性分离开来时，信息处理是最有效的。<ref name="NTC" />这些偏离引起瞬态或暂时的变化，这些变化在设备的输出中得到了体现。<ref name="NTC" />

==== Deep reservoir computing ====

−

The extension of the reservoir computing framework towards Deep Learning, with the introduction of Deep Reservoir Computing and of the Deep Echo State Network (DeepESN) model<ref>{{cite thesis |type=PhD thesis |last=Pedrelli |first=Luca |date=2019 |title=Deep Reservoir Computing: A Novel Class of Deep Recurrent Neural Networks |publisher=Università di Pisa |url=https://etd.adm.unipi.it/t/etd-02282019-191815/}}</ref><ref>{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|last3=Pedrelli|first3=Luca|title=Deep reservoir computing: A critical experimental analysis|journal=Neurocomputing|volume=268|pages=87–99|doi=10.1016/j.neucom.2016.12.089|date=2017-12-13|hdl=11568/851934|hdl-access=free}}</ref><ref>{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|date=2017-05-05|title=Echo State Property of Deep Reservoir Computing Networks|journal=Cognitive Computation|volume=9|issue=3|pages=337–350|doi=10.1007/s12559-017-9461-9|issn=1866-9956|hdl=11568/851932|s2cid=1077549|hdl-access=free}}</ref><ref>{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|last3=Pedrelli|first3=Luca|date=December 2018|title=Design of deep echo state networks|journal=Neural Networks|volume=108|pages=33–47|doi=10.1016/j.neunet.2018.08.002|pmid=30138751|issn=0893-6080|hdl=11568/939082|s2cid=52075702|hdl-access=free}}</ref> allows to develop efficiently trained models for hierarchical processing of temporal data, at the same time enabling the investigation on the inherent role of layered composition in [[recurrent neural network]]s.

+

The extension of the reservoir computing framework towards Deep Learning, with the introduction of Deep Reservoir Computing and of the Deep Echo State Network (DeepESN) model<ref name=":16">{{cite thesis |type=PhD thesis |last=Pedrelli |first=Luca |date=2019 |title=Deep Reservoir Computing: A Novel Class of Deep Recurrent Neural Networks |publisher=Università di Pisa |url=https://etd.adm.unipi.it/t/etd-02282019-191815/}}</ref><ref name=":17">{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|last3=Pedrelli|first3=Luca|title=Deep reservoir computing: A critical experimental analysis|journal=Neurocomputing|volume=268|pages=87–99|doi=10.1016/j.neucom.2016.12.089|date=2017-12-13|hdl=11568/851934|hdl-access=free}}</ref><ref name=":18">{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|date=2017-05-05|title=Echo State Property of Deep Reservoir Computing Networks|journal=Cognitive Computation|volume=9|issue=3|pages=337–350|doi=10.1007/s12559-017-9461-9|issn=1866-9956|hdl=11568/851932|s2cid=1077549|hdl-access=free}}</ref><ref name=":19">{{Cite journal|last1=Gallicchio|first1=Claudio|last2=Micheli|first2=Alessio|last3=Pedrelli|first3=Luca|date=December 2018|title=Design of deep echo state networks|journal=Neural Networks|volume=108|pages=33–47|doi=10.1016/j.neunet.2018.08.002|pmid=30138751|issn=0893-6080|hdl=11568/939082|s2cid=52075702|hdl-access=free}}</ref> allows to develop efficiently trained models for hierarchical processing of temporal data, at the same time enabling the investigation on the inherent role of layered composition in [[recurrent neural network]]s.

The extension of the reservoir computing framework towards Deep Learning, with the introduction of Deep Reservoir Computing and of the Deep Echo State Network (DeepESN) model allows to develop efficiently trained models for hierarchical processing of temporal data, at the same time enabling the investigation on the inherent role of layered composition in recurrent neural networks.

第129行：第129行：

深度储备池计算

−

随着深度储备池计算和深度回波状态网络(DeepESN)模型的出现，储备池计算框架开始向深度学习扩展，发展了有效的可训练模型来对时间数据进行多层次处理，同时使层状组合在循环神经网络中的固有作用的研究得以进行。

+

随着深度储备池计算和深度回波状态网络(DeepESN)模型<ref name=":16" /><ref name=":17" /><ref name=":18" /><ref name=":19" />的出现，储备池计算框架开始向深度学习扩展，发展了有效的可训练模型来对时间数据进行多层次处理，同时使层状组合在循环神经网络中的固有作用的研究得以进行。

== Quantum reservoir computing ==

第138行：第138行：

量子储备池计算

−

量子储备池计算可以利用量子力学相互作用的非线性本质或过程来形成具有特征的非线性储备池，也可以利用线性储备池来实现，即向储备池注入输入来产生非线性。机器学习和量子设备的结合，引出了一个新的研究领域——量子神经形态计算

+

量子储备池计算可以利用量子力学相互作用的非线性本质或过程来形成具有特征的非线性储备池<ref name=":2" /><ref name=":3" /><ref name="CN19" /><ref name="JNY20" />，也可以利用线性储备池来实现，即向储备池注入输入来产生非线性。<ref name=":5" />机器学习和量子设备的结合，引出了一个新的研究领域——量子神经形态计算。<ref name="MG20" />

=== Types ===

第152行：第152行：

= = = 相互作用的量子谐振子的高斯态 = = =

−

Gaussian states are a paradigmatic class of states of [[Continuous-variable quantum information|continuous variable quantum systems]].<ref>{{cite arXiv|last1=Ferraro|first1=Alessandro|last2=Olivares|first2=Stefano|last3=Paris|first3=Matteo G. A.|date=2005-03-31|title=Gaussian states in continuous variable quantum information|eprint=quant-ph/0503237}}</ref> Although they can nowadays be created and manipulated in, e.g, state-of-the-art optical platforms,<ref>{{Cite journal|last1=Roslund|first1=Jonathan|last2=de Araújo|first2=Renné Medeiros|last3=Jiang|first3=Shifeng|last4=Fabre|first4=Claude|last5=Treps|first5=Nicolas|date=2013-12-15|title=Wavelength-multiplexed quantum networks with ultrafast frequency combs|url=https://www.nature.com/articles/nphoton.2013.340|journal=Nature Photonics|language=en|volume=8|issue=2|pages=109–112|doi=10.1038/nphoton.2013.340|arxiv=1307.1216|s2cid=2328402|issn=1749-4893}}</ref> naturally robust to [[Quantum decoherence|decoherence]], it is well-known that they are not sufficient for, e.g., universal [[quantum computing]] because transformations that preserve the Gaussian nature of a state are linear.<ref>{{Cite journal|last1=Bartlett|first1=Stephen D.|last2=Sanders|first2=Barry C.|last3=Braunstein|first3=Samuel L.|last4=Nemoto|first4=Kae|date=2002-02-14|title=Efficient Classical Simulation of Continuous Variable Quantum Information Processes|url=https://link.aps.org/doi/10.1103/PhysRevLett.88.097904|journal=Physical Review Letters|volume=88|issue=9|pages=097904|doi=10.1103/PhysRevLett.88.097904|pmid=11864057|arxiv=quant-ph/0109047|bibcode=2002PhRvL..88i7904B|s2cid=2161585}}</ref> Normally, linear dynamics would not be sufficient for nontrivial reservoir computing either. It is nevertheless possible to harness such dynamics for reservoir computing purposes by considering a network of interacting [[quantum harmonic oscillator]]s and injecting the input by periodical state resets of a subset of the oscillators. With a suitable choice of how the states of this subset of oscillators depends on the input, the observables of the rest of the oscillators can become nonlinear functions of the input suitable for reservoir computing; indeed, thanks to the properties of these functions, even universal reservoir computing becomes possible by combining the observables with a polynomial readout function.<ref name=":5" /> In principle, such reservoir computers could be implemented with controlled multimode [[Optical parametric oscillator|optical parametric processes]],<ref>{{Cite journal|last1=Nokkala|first1=J.|last2=Arzani|first2=F.|last3=Galve|first3=F.|last4=Zambrini|first4=R.|last5=Maniscalco|first5=S.|last6=Piilo|first6=J.|last7=Treps|first7=N.|last8=Parigi|first8=V.|date=2018-05-09|title=Reconfigurable optical implementation of quantum complex networks|url=https://doi.org/10.1088%2F1367-2630%2Faabc77|journal=New Journal of Physics|language=en|volume=20|issue=5|pages=053024|doi=10.1088/1367-2630/aabc77|arxiv=1708.08726|bibcode=2018NJPh...20e3024N|s2cid=119091176|issn=1367-2630}}</ref> however efficient extraction of the output from the system is challenging especially in the quantum regime where [[Measurement in quantum mechanics#State change due to measurement|measurement back-action]] must be taken into account.

+

Gaussian states are a paradigmatic class of states of [[Continuous-variable quantum information|continuous variable quantum systems]].<ref name=":20">{{cite arXiv|last1=Ferraro|first1=Alessandro|last2=Olivares|first2=Stefano|last3=Paris|first3=Matteo G. A.|date=2005-03-31|title=Gaussian states in continuous variable quantum information|eprint=quant-ph/0503237}}</ref> Although they can nowadays be created and manipulated in, e.g, state-of-the-art optical platforms,<ref name=":21">{{Cite journal|last1=Roslund|first1=Jonathan|last2=de Araújo|first2=Renné Medeiros|last3=Jiang|first3=Shifeng|last4=Fabre|first4=Claude|last5=Treps|first5=Nicolas|date=2013-12-15|title=Wavelength-multiplexed quantum networks with ultrafast frequency combs|url=https://www.nature.com/articles/nphoton.2013.340|journal=Nature Photonics|language=en|volume=8|issue=2|pages=109–112|doi=10.1038/nphoton.2013.340|arxiv=1307.1216|s2cid=2328402|issn=1749-4893}}</ref> naturally robust to [[Quantum decoherence|decoherence]], it is well-known that they are not sufficient for, e.g., universal [[quantum computing]] because transformations that preserve the Gaussian nature of a state are linear.<ref name=":22">{{Cite journal|last1=Bartlett|first1=Stephen D.|last2=Sanders|first2=Barry C.|last3=Braunstein|first3=Samuel L.|last4=Nemoto|first4=Kae|date=2002-02-14|title=Efficient Classical Simulation of Continuous Variable Quantum Information Processes|url=https://link.aps.org/doi/10.1103/PhysRevLett.88.097904|journal=Physical Review Letters|volume=88|issue=9|pages=097904|doi=10.1103/PhysRevLett.88.097904|pmid=11864057|arxiv=quant-ph/0109047|bibcode=2002PhRvL..88i7904B|s2cid=2161585}}</ref> Normally, linear dynamics would not be sufficient for nontrivial reservoir computing either. It is nevertheless possible to harness such dynamics for reservoir computing purposes by considering a network of interacting [[quantum harmonic oscillator]]s and injecting the input by periodical state resets of a subset of the oscillators. With a suitable choice of how the states of this subset of oscillators depends on the input, the observables of the rest of the oscillators can become nonlinear functions of the input suitable for reservoir computing; indeed, thanks to the properties of these functions, even universal reservoir computing becomes possible by combining the observables with a polynomial readout function.<ref name=":5" /> In principle, such reservoir computers could be implemented with controlled multimode [[Optical parametric oscillator|optical parametric processes]],<ref name=":23">{{Cite journal|last1=Nokkala|first1=J.|last2=Arzani|first2=F.|last3=Galve|first3=F.|last4=Zambrini|first4=R.|last5=Maniscalco|first5=S.|last6=Piilo|first6=J.|last7=Treps|first7=N.|last8=Parigi|first8=V.|date=2018-05-09|title=Reconfigurable optical implementation of quantum complex networks|url=https://doi.org/10.1088%2F1367-2630%2Faabc77|journal=New Journal of Physics|language=en|volume=20|issue=5|pages=053024|doi=10.1088/1367-2630/aabc77|arxiv=1708.08726|bibcode=2018NJPh...20e3024N|s2cid=119091176|issn=1367-2630}}</ref> however efficient extraction of the output from the system is challenging especially in the quantum regime where [[Measurement in quantum mechanics#State change due to measurement|measurement back-action]] must be taken into account.

Gaussian states are a paradigmatic class of states of continuous variable quantum systems. Although they can nowadays be created and manipulated in, e.g, state-of-the-art optical platforms, naturally robust to decoherence, it is well-known that they are not sufficient for, e.g., universal quantum computing because transformations that preserve the Gaussian nature of a state are linear. Normally, linear dynamics would not be sufficient for nontrivial reservoir computing either. It is nevertheless possible to harness such dynamics for reservoir computing purposes by considering a network of interacting quantum harmonic oscillators and injecting the input by periodical state resets of a subset of the oscillators. With a suitable choice of how the states of this subset of oscillators depends on the input, the observables of the rest of the oscillators can become nonlinear functions of the input suitable for reservoir computing; indeed, thanks to the properties of these functions, even universal reservoir computing becomes possible by combining the observables with a polynomial readout function. In principle, such reservoir computers could be implemented with controlled multimode optical parametric processes, however efficient extraction of the output from the system is challenging especially in the quantum regime where measurement back-action must be taken into account.

−

高斯态是连续变量量子系统的一类典型态。尽管它们现在可以在最先进的光学平台上创建和操作，这些平台对去相干具有天然的鲁棒性，但众所周知，它们对于通用量子计算来说是不够的，因为保持状态的高斯性质的变换是线性的。正常情况下，线性动力学也不足以进行非平凡的储层计算。然而，通过考虑一个由相互作用的量子谐振子组成的网络，并通过周期性的振子子集的状态重置注入输入，可以将这种动力学应用于储备池计算目的。选择一个合适的振荡器子集的状态如何取决于输入，其余振荡器的观测量可以成为非线性函数的输入适合于储备池计算; 事实上，由于这些函数的性质，甚至通用储备池计算成为可能，通过结合观测量和一个多项式读出函数。原则上，这种储备池计算机可以通过受控的多模光学参量过程实现，但是从系统中有效地提取输出是一个挑战，特别是在必须考虑测量反作用的量子体制中。

+

高斯态是连续变量量子系统的一类典型态。<ref name=":20" />尽管它们现在可以在最先进的光学平台上创建和操作，这些平台对去相干具有天然的鲁棒性<ref name=":21" />，但众所周知，它们对于通用量子计算来说是不够的，因为保持状态的高斯性质的变换是线性的。<ref name=":22" />正常情况下，线性动力学也不足以进行非平凡的储层计算。然而，通过考虑一个由相互作用的量子谐振子组成的网络，并通过周期性的振子子集的状态重置注入输入，可以将这种动力学应用于储备池计算目的。选择一个合适的振荡器子集的状态如何取决于输入，其余振荡器的观测量可以成为非线性函数的输入适合于储备池计算; 事实上，由于这些函数的性质，甚至通用储备池计算成为可能，通过结合观测量和一个多项式读出函数。<ref name=":5" />原则上，这种储备池计算机可以通过受控的多模光学参量过程实现<ref name=":23" />，但是从系统中有效地提取输出是一个挑战，特别是在必须考虑测量反作用的量子体制中。

==== 2-D quantum dot lattices ====

第165行：第165行：

2-D 量子点格子

−

在这种结构中，格点之间的随机耦合赋予了储备池处理器固有的“黑盒”属性。然后通过一个入射光场激发储存器，作为输入。读出以格点的职业数的形式出现，这是输入的自然非线性函数。

+

在这种结构中，格点之间的随机耦合赋予了储备池处理器固有的“黑盒”属性。<ref name=":2" />然后通过一个入射光场激发储存器，作为输入。读出以格点的职业数的形式出现，这是输入的自然非线性函数。<ref name=":2" />

==== Nuclear spins in a molecular solid ====

第172行：第172行：

In this architecture, quantum mechanical coupling between spins of neighboring atoms within the molecular solid provides the non-linearity required to create the higher-dimensional computational space. The reservoir is then excited by radiofrequency electromagnetic radiation tuned to the resonance frequencies of relevant nuclear spins. Readout occurs by measuring the nuclear spin states.

−

分子固体中的核自旋在这种结构中，分子固体中相邻原子自旋之间的量子力学耦合提供了创造高维计算空间所需的非线性。然后，该储备池被调谐到相关核自旋共振频率的射频电磁辐射所激发。通过测量原子核的自旋态就可以读出数据。

+

分子固体中的核自旋在这种结构中，分子固体中相邻原子自旋之间的量子力学耦合提供了创造高维计算空间所需的非线性。<ref name=":3" />然后，该储备池被调谐到相关核自旋共振频率的射频电磁辐射所激发。通过测量原子核的自旋态就可以读出数据。<ref name=":3" />

==== Reservoir computing on gate-based near-term superconducting quantum computers ====

−

The most prevalent model of quantum computing is the gate-based model where quantum computation is performed by sequential applications of unitary quantum gates on qubits of a quantum computer.<ref>{{Citation|last1=Nielsen|first1=Michael|last2=Chuang|first2=Isaac|title=Quantum Computation and Quantum Information|publisher=Cambridge University Press Cambridge|date=2010|edition=2}}</ref> A theory for the implementation of reservoir computing on a gate-based quantum computer with proof-of-principle demonstrations on a number of IBM superconducting [[NISQ era|noisy intermediate-scale quantum]] (NISQ) computers<ref>[[John Preskill]]. "Quantum Computing in the NISQ era and beyond." Quantum 2,79 (2018)</ref> has been reported in.<ref name="JNY20"/>

+

The most prevalent model of quantum computing is the gate-based model where quantum computation is performed by sequential applications of unitary quantum gates on qubits of a quantum computer.<ref name=":24">{{Citation|last1=Nielsen|first1=Michael|last2=Chuang|first2=Isaac|title=Quantum Computation and Quantum Information|publisher=Cambridge University Press Cambridge|date=2010|edition=2}}</ref> A theory for the implementation of reservoir computing on a gate-based quantum computer with proof-of-principle demonstrations on a number of IBM superconducting [[NISQ era|noisy intermediate-scale quantum]] (NISQ) computers<ref name=":25">[[John Preskill]]. "Quantum Computing in the NISQ era and beyond." Quantum 2,79 (2018)</ref> has been reported in.<ref name="JNY20"/>

The most prevalent model of quantum computing is the gate-based model where quantum computation is performed by sequential applications of unitary quantum gates on qubits of a quantum computer. A theory for the implementation of reservoir computing on a gate-based quantum computer with proof-of-principle demonstrations on a number of IBM superconducting noisy intermediate-scale quantum (NISQ) computersJohn Preskill. "Quantum Computing in the NISQ era and beyond." Quantum 2,79 (2018) has been reported in.

第181行：第181行：

基于门的近期超导量子计算机上的储备池计算

−

量子计算最流行的模型是基于门的模型，量子计算是通过量子计算机量子比特上的幺正量子门顺序应用来执行的。在基于栅极的量子计算机上实现储备池计算的理论，并在 IBM 超导带噪中级量子计算机(NISQ)上进行了原理论证。

+

量子计算最流行的模型是基于门的模型，量子计算是通过量子计算机量子比特上的幺正量子门顺序应用来执行的。<ref name=":24" />在基于栅极的量子计算机上实现储备池计算的理论，并在 IBM 超导带噪中级量子计算机(NISQ)<ref name=":25" />上进行了原理论证。<ref name="JNY20" />

== See also ==

1210080212

20

个编辑

更改

储备池计算 (查看源代码)

2022年6月6日 (一) 15:49的版本

导航菜单

搜索