Learning invariance from transformation sequences
Neural Computation
The Design and Use of Steerable Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence
Support Vector Machines for 3D Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
A model of computation in neocortical architecture
Neural Networks - Special issue on organisation of computation in brain-like systems
Computation of pattern invariance in brain-like structures
Neural Networks - Special issue on organisation of computation in brain-like systems
Slow feature analysis: unsupervised learning of invariances
Neural Computation
Learning to recognize three-dimensional objects
Neural Computation
A Competitive-Layer Model for Feature Binding and Sensory Segmentation
Neural Computation
Minimizing Binding Errors Using Learned Conjunctive Features
Neural Computation
A Neural Network Architecture for Visual Selection
Neural Computation
Face recognition: a convolutional neural-network approach
IEEE Transactions on Neural Networks
An evaluation of the neocognitron
IEEE Transactions on Neural Networks
Maplets for correspondence-based object recognition
Neural Networks - 2004 Special issue: New developments in self-organizing systems
A cell assembly based model for the cortical microcircuitry
Neurocomputing
Robust Object Recognition with Cortex-Like Mechanisms
IEEE Transactions on Pattern Analysis and Machine Intelligence
Maximal Causes for Non-linear Component Extraction
The Journal of Machine Learning Research
Deep learning from temporal coherence in video
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Large-Scale Real-Time Object Identification Based on Analytic Features
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
A dynamic attention system that reorients to unexpected motion in real-world traffic environments
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A biologically-inspired vision architecture for resource-constrained intelligent vehicles
Computer Vision and Image Understanding
Template matching for large transformations
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
A comparison of features in parts-based object recognition hierarchies
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Color object recognition in real-world scenes
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Word recognition with a hierarchical neural network
NOLISP'07 Proceedings of the 2007 international conference on Advances in nonlinear speech processing
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
An integrated system for incremental learning of multiple visual categories
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Autonomous generation of internal representations for associative learning
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Proceedings of the sixteenth international conference on Architectural support for programming languages and operating systems
A hierarchical framework for spectro-temporal feature extraction
Speech Communication
Invariant object recognition and pose estimation with slow feature analysis
Neural Computation
A biologically motivated system for unconstrained online learning of visual objects
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Rapid online learning of objects in a biologically motivated recognition architecture
PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition
Class-Specific sparse coding for learning of object representations
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Online learning for object recognition with a hierarchical visual cortex model
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part II
Computational Intelligence and Neuroscience
Hierarchical kernel-based rotation and scale invariant similarity
Pattern Recognition
Hi-index | 0.00 |
There is an ongoing debate over the capabilities of hierarchical neural feedforward architectures for performing real-world invariant object recognition. Although a variety of hierarchical models exists, appropriate supervised and unsupervised learning methods are still an issue of intense research. We propose a feedforward model for recognition that shares components like weight sharing, pooling stages, and competitive nonlinearities with earlier approaches but focuses on new methods for learning optimal feature-detecting cells in intermediate stages of the hierarchical network. We show that principles of sparse coding, which were previously mostly applied to the initial feature detection stages, can also be employed to obtain optimized intermediate complex features. We suggest a new approach to optimize the learning of sparse features under the constraints of a weight-sharing or convolutional architecture that uses pooling operations to achieve gradual invariance in the feature hierarchy. The approach explicitly enforces symmetry constraints like translation invariance on the feature set. This leads to a dimension reduction in the search space of optimal features and allows determining more efficiently the basis representatives, which achieve a sparse decomposition of the input. We analyze the quality of the learned feature representation by investigating the recognition performance of the resulting hierarchical network on object and face databases. We show that a hierarchy with features learned on a single object data set can also be applied to face recognition without parameter changes and is competitive with other recent machine learning recognition approaches. To investigate the effect of the interplay between sparse coding and processing nonlinearities, we also consider alternative feedforward pooling nonlinearities such as presynaptic maximum selection and sum-of-squares integration. The comparison shows that a combination of strong competitive nonlinearities with sparse coding offers the best recognition performance in the difficult scenario of segmentation-free recognition in cluttered surround. We demonstrate that for both learning and recognition, a precise segmentation of the objects is not necessary.