Optimal Linear Combination of Neural Networks for Improving Classification Performance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Object Recognition with Features Inspired by Visual Cortex
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Semilinear predictability minimization produces well-known feature detectors
Neural Computation
Evaluation of pooling operations in convolutional architectures for object recognition
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Deep, big, simple neural nets for handwritten digit recognition
Neural Computation
ICDAR 2011 Chinese Handwriting Recognition Competition
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
Convolutional Neural Network Committees for Handwritten Character Classification
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
Better Digit Recognition with a Committee of Simple Neural Nets
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
Flexible, high performance convolutional neural networks for image classification
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Improving model accuracy using optimal linear combinations of trained neural networks
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combining various DNNs trained on differently preprocessed data into a Multi-Column DNN (MCDNN) further boosts recognition performance, making the system insensitive also to variations in contrast and illumination.