A trainable feature extractor for handwritten digit recognition

DOI10.1016/j.patcog.2006.10.011zbMath1114.68515OpenAlexW2170393096MaRDI QIDQ877139

Gérard Bloch, Fabien Lauer, Ching-Yun Suen

Publication date: 19 April 2007

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.patcog.2006.10.011

zbMATH Keywords

feature extractionsupport vector machinescharacter recognitionconvolutional neural networkselastic distortion

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items

Apportioned margin approach for cost sensitive large margin classifiers ⋮ Privacy-preserving distributed deep learning based on secret sharing ⋮ An adaptive deep Q-learning strategy for handwritten digit recognition ⋮ Complex system fault diagnosis based on a fuzzy robust wavelet support vector classifier and an adaptive Gaussian particle swarm optimization ⋮ Nonlinear dimensionality reduction using a temporal coherence principle ⋮ Neural networks for radar waveform recognition

Uses Software

• MNIST

Cites Work

• Multicategory classification by support vector machines
• Combining discriminant models with new multi-class SVMs
• 10.1162/15324430260185628
• 10.1162/153244303322753616
• Choosing multiple parameters for support vector machines
• Training invariant support vector machines
• Unnamed Item
• Unnamed Item