دسته بندی:
محاسبات کوانتومی - Quantum-Computing
سال انتشار:
2022
عنوان انگلیسی مقاله:
High-Performance Reservoir Computing With Fluctuations in Linear Networks
ترجمه فارسی عنوان مقاله:
محاسبات مخزن با کارایی بالا با نوسانات در شبکه های خطی
منبع:
ieee - ieee Transactions on Neural Networks and Learning Systems;2022;33;6;10:1109/TNNLS:2021:3105695
نویسنده:
Johannes Nokkala; Rodrigo Martinez-Pena; Roberta Zambrini; Miguel C. Soriano
چکیده انگلیسی:
Reservoir computing has emerged as a powerful
machine learning paradigm for harvesting nontrivial information
processing out of disordered physical systems driven by sequential inputs. To this end, the system observables must become
nonlinear functions of the input history. We show that encoding
the input to quantum or classical fluctuations of a network of
interacting harmonic oscillators can lead to a high performance
comparable to that of a standard echo state network in several
nonlinear benchmark tasks. This equivalence in performance
holds even with a linear Hamiltonian and a readout linear in the
system observables. Furthermore, we find that the performance of
the network of harmonic oscillators in nonlinear tasks is robust to
errors both in input and reservoir observables caused by external
noise. For any reservoir computing system with a linear readout,
the magnitude of trained weights can either amplify or suppress
noise added to reservoir observables. We use this general result to
explain why the oscillators are robust to noise and why having
precise control over reservoir memory is important for noise
robustness in general. Our results pave the way toward reservoir
computing harnessing fluctuations in disordered linear systems.
Index Terms: Dynamical systems | machine learning | quantum mechanics | recurrent neural networks | reservoir computing | supervised learning.
قیمت: رایگان
توضیحات اضافی:
تعداد نظرات : 0