article Open AccessTop 1% cited
Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
Neural Computation · 2010 · Vol. 22(12) · pp. 3207–3220
Dan Claudiu Cireşan✉(Università della Svizzera italiana)Ueli Meier(Dalle Molle Institute for Artificial Intelligence Research)Luca Maria Gambardella(Università della Svizzera italiana)Jürgen Schmidhuber(Dalle Molle Institute for Artificial Intelligence Research)
Abstract
Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35% error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images to avoid overfitting, and graphics cards to greatly speed up learning.
Handwritten Text Recognition TechniquesImage Processing and 3D ReconstructionVehicle License Plate RecognitionSimple (philosophy)Computer scienceDigit recognitionArtificial neural networkPattern recognition (psychology)Numerical digitSpeech recognitionArtificial intelligenceDeep neural networksArithmetic
MeSH terms
AlgorithmsArtificial IntelligenceHandwritingPattern Recognition, Automated
Funding
- Kommission für Technologie und Innovation
Citations
1,058
FWCI
32.34
field-weighted impact
References
31
Percentile
100%
vs. same field & year
Citations per year
Cited by
Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks
IEEE Transactions on Biomedical Engineering · 2015 · 1,797 citations
Empirical Mode Decomposition based ensemble deep learning for load demand time series forecasting
Applied Soft Computing · 2017 · 447 citations
Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks
IEEE Transactions on Industrial Electronics · 2016 · 1,333 citations
Big Data Deep Learning: Challenges and Perspectives
IEEE Access · 2014 · 1,248 citations
A novel hybrid CNN–SVM classifier for recognizing handwritten digits
Pattern Recognition · 2011 · 666 citations
Machine learning of molecular electronic properties in chemical compound space
New Journal of Physics · 2013 · 621 citations
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies
Journal of Chemical Theory and Computation · 2013 · 634 citations
A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications
Mechanical Systems and Signal Processing · 2020 · 1,273 citations
References
Long Short-Term Memory
Neural Computation · 1997 · 95,078 citations
Reducing the Dimensionality of Data with Neural Networks
Science · 2006 · 20,627 citations
Gradient-based learning applied to document recognition
Proceedings of the IEEE · 1998 · 57,014 citations
Artificial intelligence: a modern approach
Choice Reviews Online · 1995 · 22,209 citations
Citation Network
How this paper connects to the literature. Drag to explore, click any node to open that paper.