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
A fast learning algorithm for deep belief nets
Neural Computation
The Application of a Convolution Neural Network on Face and License Plate Detection
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Boosting products of base classifiers
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Deep learning from temporal coherence in video
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Introduction to Algorithms, Third Edition
Introduction to Algorithms, Third Edition
A Fast and Stable Incremental Clustering Algorithm
ITNG '10 Proceedings of the 2010 Seventh International Conference on Information Technology: New Generations
Research frontier: deep machine learning--a new frontier in artificial intelligence research
IEEE Computational Intelligence Magazine
Deep Spatiotemporal Feature Learning with Application to Image Classification
ICMLA '10 Proceedings of the 2010 Ninth International Conference on Machine Learning and Applications
Unsupervised learning of hierarchical representations with convolutional deep belief networks
Communications of the ACM
Hi-index | 0.10 |
Deep machine learning offers a comprehensive framework for extracting meaningful features from complex observations in an unsupervised manner. The majority of deep learning architectures described in the literature primarily focus on extracting spatial features. However, in real-world settings, capturing temporal dependencies in observations is critical for accurate inference. This paper introduces an enhancement to DeSTIN - a compositional deep learning architecture in which each layer consists of multiple instantiations of a common node - that learns to represent spatiotemporal patterns in data based on a novel recurrent clustering algorithm. Contrary to mainstream deep architectures, such as deep belief networks where layer-by-layer training is assumed, each of the nodes in the proposed architecture is trained independently and in parallel. Moreover, top-down and bottom-up information flows facilitate rich feature formation. A semi-supervised setting is demonstrated achieving state-of-the-art results on the MNIST classification benchmarks. A GPU implementation is discussed further accentuating the scalability properties of the proposed framework.