Sequential analysis in Fourier probabilistic neural networks

作者：

Highlights：

• Image recognition with high-dimensional deep embeddings may be slow.

• Fourier series estimates improves performance of probabilistic neural network (PNN).

• Sequential Fourier PNN is proposed for principal components of deep embeddings.

• Sequential Fourier PNN is faster and more accurate than known modifications of PNN.

摘要

•Image recognition with high-dimensional deep embeddings may be slow.•Fourier series estimates improves performance of probabilistic neural network (PNN).•Sequential Fourier PNN is proposed for principal components of deep embeddings.•Sequential Fourier PNN is faster and more accurate than known modifications of PNN.

论文关键词：Image recognition,Probabilistic neural network (PNN),Fourier series,Orthogonal series kernel,Sequential analysis,Convolutional neural network (CNN)

论文评审过程：Received 15 January 2021, Revised 21 March 2022, Accepted 14 June 2022, Available online 20 June 2022, Version of Record 28 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117885