Mostra i principali dati dell'item
Fuzzy Pooling
dc.creator | Diamantis D.E., Iakovidis D.K. | en |
dc.date.accessioned | 2023-01-31T07:54:45Z | |
dc.date.available | 2023-01-31T07:54:45Z | |
dc.date.issued | 2021 | |
dc.identifier | 10.1109/TFUZZ.2020.3024023 | |
dc.identifier.issn | 10636706 | |
dc.identifier.uri | http://hdl.handle.net/11615/73268 | |
dc.description.abstract | Convolutional neural networks (CNNs) are artificial learning systems typically based on two operations: convolution, which implements feature extraction through filtering, and pooling, which implements dimensionality reduction. The impact of pooling in the classification performance of the CNNs has been highlighted in several previous works, and a variety of alternative pooling operators have been proposed. However, only a few of them tackle with the uncertainty that is naturally propagated from the input layer to the feature maps of the hidden layers through convolutions. In this article we present a novel pooling operation based on (type-1) fuzzy sets to cope with the local imprecision of the feature maps, and we investigate its performance in the context of image classification. Fuzzy pooling is performed by fuzzification, aggregation, and defuzzification of feature map neighborhoods. It is used for the construction of a fuzzy pooling layer that can be applied as a drop-in replacement of the current, crisp, pooling layers of CNN architectures. Several experiments using publicly available datasets show that the proposed approach can enhance the classification performance of a CNN. A comparative evaluation shows that it outperforms state-of-the-art pooling approaches. © 2020 IEEE. | en |
dc.language.iso | en | en |
dc.source | IEEE Transactions on Fuzzy Systems | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140763484&doi=10.1109%2fTFUZZ.2020.3024023&partnerID=40&md5=e05e381310d6dc6d11e9f8605b368e2e | |
dc.subject | Convolution | en |
dc.subject | Convolutional neural networks | en |
dc.subject | Fuzzy inference | en |
dc.subject | Fuzzy neural networks | en |
dc.subject | Fuzzy sets | en |
dc.subject | Image classification | en |
dc.subject | Learning systems | en |
dc.subject | Artificial learning | en |
dc.subject | Classification performance | en |
dc.subject | Convolutional neural network | en |
dc.subject | Dimensionality reduction | en |
dc.subject | Feature map | en |
dc.subject | Features extraction | en |
dc.subject | Image-analysis | en |
dc.subject | Pooling | en |
dc.subject | Uncertainty | en |
dc.subject | Classification (of information) | en |
dc.subject | Institute of Electrical and Electronics Engineers Inc. | en |
dc.title | Fuzzy Pooling | en |
dc.type | journalArticle | en |
Files in questo item
Files | Dimensione | Formato | Mostra |
---|---|---|---|
Nessun files in questo item. |