Interval type-2 fuzzy sets for enhanced learning in deep belief networks

Shukla, Amit K.; Seth, Taniya; Muhuri, Pranab K.

doi:10.1109/fuzz-ieee.2017.8015638

Cited by 16 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[22] proposed a fuzzy restricted Boltzmann machine (FRBM) where parameters in the model are fuzzy numbers. [23] extended FRBM with Pythagorean fuzzy numbers [24] and applied the model for airline passenger profiling, and [25] extended FRBM with interval Type-2 fuzzy numbers [26]. [27] used Pythagorean fuzzy values to express distribution of parameters in a deep denoising auto-encoder and applied it for early warning of industrial accident.…”

Section: Deep Neuro-fuzzy Structuresmentioning

confidence: 99%

A Deep Neuro-Fuzzy Network for Image Classification

Yazdanbakhsh¹,

Dick²

2020

Preprint

View full text Add to dashboard Cite

The combination of neural network and fuzzy systems into neuro-fuzzy systems integrates fuzzy reasoning rules into the connectionist networks. However, the existing neuro-fuzzy systems are developed under shallow structures having lower generalization capacity. We propose the first end-to-end deep neuro-fuzzy network and investigate its application for image classification. Two new operations are developed based on definitions of Takagi-Sugeno-Kang (TSK) fuzzy model namely fuzzy inference operation and fuzzy pooling operations; stacks of these operations comprise the layers in this network. We evaluate the network on MNIST, CIFAR-10 and CIFAR-100 datasets, finding that the network has a reasonable accuracy in these benchmarks.Preprint. Under review.

show abstract