TY - GEN

T1 - Image Processing with Reservoir Neural Network

AU - Tarkov, Mikhail S.

AU - Ivanova, Victoria V.

PY - 2023

Y1 - 2023

N2 - Reservoir neural network (RNN) is a powerful tool for solving complex machine learning problems. The reservoir is a recurrent part of the network having a large size and rare internal connections which are most often set randomly and remain fixed. The idea of the RNN is to train only part of the network using a simple classification/regression technique and leave most of the network (reservoir) fixed. At the same time, all RNN advantages are preserved, and the training time is significantly reduced. The work performed optimization and research of methods that improve the reservoir ability to solve problems of image classification. These methods are based on the reservoir output data transformation before they are fed to the RNN output layer. In the work, the optimal parameters values for the methods Infomax and SpaRCe were obtained, which provide a minimum error in image classification. Using the example of image classification from the MNIST handwritten digit database, it is shown that: 1. Reservoir networks are trained much faster than convolutional networks, although they are inferior to the latter in terms of image classification accuracy. 2. ESN (echo-state network) with principal component projector (PCA) gives more accurate results than ESN, Infomax and SpaRCe networks, but is slower.

AB - Reservoir neural network (RNN) is a powerful tool for solving complex machine learning problems. The reservoir is a recurrent part of the network having a large size and rare internal connections which are most often set randomly and remain fixed. The idea of the RNN is to train only part of the network using a simple classification/regression technique and leave most of the network (reservoir) fixed. At the same time, all RNN advantages are preserved, and the training time is significantly reduced. The work performed optimization and research of methods that improve the reservoir ability to solve problems of image classification. These methods are based on the reservoir output data transformation before they are fed to the RNN output layer. In the work, the optimal parameters values for the methods Infomax and SpaRCe were obtained, which provide a minimum error in image classification. Using the example of image classification from the MNIST handwritten digit database, it is shown that: 1. Reservoir networks are trained much faster than convolutional networks, although they are inferior to the latter in terms of image classification accuracy. 2. ESN (echo-state network) with principal component projector (PCA) gives more accurate results than ESN, Infomax and SpaRCe networks, but is slower.

KW - convolutional networks

KW - image recognition

KW - neural networks

KW - reservoir

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85175799811&origin=inward&txGid=9502f9629b94ccda846017b2431108c2

UR - https://www.mendeley.com/catalogue/d655f24e-5b30-33b7-b0ad-ee356ee8762a/

U2 - 10.1007/978-3-031-44865-2_36

DO - 10.1007/978-3-031-44865-2_36

M3 - Conference contribution

SN - 9783031448645

T3 - Studies in Computational Intelligence

SP - 337

EP - 345

BT - Studies in Computational Intelligence

PB - Springer Science and Business Media Deutschland GmbH

ER -