Paper Info
Title
Reservoir Computing With Untrained Convolutional Neural Networks For Image Recognition
Abstract
Reservoir computing has attracted much attention for its easy training process as well as its ability to deal with temporal data. A reservoir computing system consists of a reservoir part represented as a sparsely connected recurrent neural network and a readout part represented as a simple regression model. In machine learning tasks, the reservoir part is fixed and only the readout part is trained. Although reservoir computing has been mainly applied to time series prediction and recognition, it can be applied to image recognition as well by considering an image data as a sequence of pixel values. However, to achieve a high performance in image recognition with raw image data, a large-scale reservoir including a large number of neurons is required. This is a bottleneck in terms of computer memory and computational cost. To overcome this bottleneck, we propose a new method which combines reservoir computing with untrained convolutional neural networks. We use an untrained convolutional neural network to transform raw image data into a set of smaller feature maps in a preprocessing step of the reservoir computing. We demonstrate that our method achieves a high classification accuracy in an image recognition task with a much smaller number of trainable parameters compared with a previous study.
Year
DOI
Venue
2018
10.1109/ICPR.2018.8545471
2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)
Field
DocType
ISSN
Bottleneck,Computer vision,Pattern recognition,Convolutional neural network,Computer science,Recurrent neural network,Feature extraction,Preprocessor,Reservoir computing,Artificial intelligence,Pixel,Computer memory
Conference
1051-4651
Citations 
PageRank 
References 
1
0.35
0
Authors
2
Name
Order
Citations
PageRank
Zhiqiang Tong131.05
Gouhei Tanaka25111.80