Using Generative Models for Handwritten Digit Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Instantiating deformable models with a neural net
Computer Vision and Image Understanding
Mixtures of probabilistic principal component analyzers
Neural Computation
Boosting the margin: A new explanation for the effectiveness of voting methods
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Non-Linear Dimensionality Reduction
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Efficient Pattern Recognition Using a New Transformation Distance
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Input Reconstruction Reliability Estimation
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Constraint Tangent Distance for On-Line Character Recognition
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume IV-Volume 7472 - Volume 7472
A novelty detection approach to classification
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
A neural network-based model for paper currency recognition and verification
IEEE Transactions on Neural Networks
Modeling the manifolds of images of handwritten digits
IEEE Transactions on Neural Networks
Learning in multilayered networks used as autoassociators
IEEE Transactions on Neural Networks
One-class document classification via Neural Networks
Neurocomputing
Fusion of IR and visible light modalities for face recognition
BTAS'09 Proceedings of the 3rd IEEE international conference on Biometrics: Theory, applications and systems
Hardware/software codesign for embedded implementation of neural networks
ARC'07 Proceedings of the 3rd international conference on Reconfigurable computing: architectures, tools and applications
| Hi-index | 0.00 |
We present a new classification architecture based on autoassociative neural networks that are used to learn discriminant models of each class. The proposed architecture has several interesting properties with respect to other model-based classifiers like nearest-neighbors or radial basis functions: it has a low computational complexity and uses a compact distributed representation of the models. The classifier is also well suited for the incorporation of a priori knowledge by means of a problemspecific distance measure. In particular, we will show that tangent distance (Simard, Le Cun, & Denker, 1993) can be used to achieve transformation invariance during learning and recognition. We demonstrate the application of this classifier to optical character recognition, where it has achieved state-of-the-art results on several reference databases. Relations to other models, in particular those based on principal component analysis, are also discussed.