Accelerating CNN models for face verification with convolution theorem

DOI10.11936/BJUTXB2016120014MaRDI QIDQ4643173zbMATH OpenFDO

Authors Bo Liu, Shen Guo

Publication date 25 May 2018

zbMATH Keywords

fast Fourier transformconvolutional neural networksconvolution theoremface verification

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Numerical methods for discrete and fast Fourier transforms (65T50) Machine vision and scene understanding (68T45)

Recommendations

• A faster algorithm for reducing the computational complexity of convolutional neural networks
• Convolution accelerator designs using fast algorithms
• Method for Convolutional Neural Network Hardware Implementation Based on a Residue Number System
• A decomposable Winograd method for N-D convolution acceleration in video analysis
• Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2D and 3D Images

Cited in

(3)

• Convolution accelerator designs using fast algorithms
• A decomposable Winograd method for N-D convolution acceleration in video analysis
• A faster algorithm for reducing the computational complexity of convolutional neural networks

This page was built for publication: Accelerating CNN models for face verification with convolution theorem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4643173)