Review of neural networks for speech recognition
Neural Computation
What size net gives valid generalization?
Advances in neural information processing systems 1
Advances in neural information processing systems 2
Recognizing hand-printed letters and digits
Advances in neural information processing systems 2
Using genetic algorithms to improve pattern classification performance
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
When Are k-Nearest Neighbor and Back Propagation Accurate for Feasible Sized Sets of Examples?
Proceedings of the EURASIP Workshop 1990 on Neural Networks
Adaptive voting rules for k-nearest neighbors classifiers
Neural Computation
Evaluation of Models for the Recognition of Hadwritten Digits in Medical Forms
BSB '08 Proceedings of the 3rd Brazilian symposium on Bioinformatics: Advances in Bioinformatics and Computational Biology
Embedded surface classification in digital sports
Pattern Recognition Letters
A reliability-based RBF network ensemble model for foreign exchange rates predication
ICONIP'06 Proceedings of the 13th international conference on Neural information processing - Volume Part III
A MLP classifier for both printed and handwritten bangla numeral recognition
ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing
A robust approach to digit recognition in noisy environments
IEA/AIE'12 Proceedings of the 25th international conference on Industrial Engineering and Other Applications of Applied Intelligent Systems: advanced research in applied artificial intelligence
Learning visual obstacle detection using color histogram features
Robot Soccer World Cup XV
Hi-index | 0.01 |
Results of recent research suggest that carefully designed multiplayer neural networks with local receptive fields and shared weights may be unique in providing low error rates on handwritten digit recognition tasks. This study, however, demonstrates that these networks, radial basis function (RBF) networks, and k nearest-neighbor (kNN) classifiers, all provide similar low error rates on a large handwritten digit database. The backpropagation network is overall superior in memory usage and classification time but can provide false positive classifications when the input is not a digit. The backpropagation network also has the longest training time. The RBF classifier requires more memory and more classification time, but less training time. When high accuracy is warranted, the RBF classifier can generate a more effective confidence judgment for rejecting ambiguous inputs. The simple kNN classifier can also perform handwritten digit recognition, but requires a prohibitively large amount of memory and is much slower at classification. Nevertheless, the simplicity of the algorithm and fast training characteristics makes the kNN classifier an attractive candidate in hardware-assisted classification tasks. These results on a large, high input dimensional problem demonstrate that practical constraints including training time, memory usage, and classification time often constrain classifier selection more strongly than small differences in overall error rate.