Introduction to the theory of neural computation
Introduction to the theory of neural computation
Learning invariance from transformation sequences
Neural Computation
Elements of information theory
Elements of information theory
Fundamentals of statistical signal processing: estimation theory
Fundamentals of statistical signal processing: estimation theory
What is the goal of sensory coding?
Neural Computation
Learning in graphical models
Dynamic Programming and Optimal Control
Dynamic Programming and Optimal Control
Approximate inference in Boltzmann machines
Artificial Intelligence
Dictionary learning algorithms for sparse representation
Neural Computation
Energy-based models for sparse overcomplete representations
The Journal of Machine Learning Research
On Intelligence
Feedforward, feedback and inhibitory connections in primate visual cortex
Neural Networks - 2004 Special issue Vision and brain
Restoring partly occluded patterns: a neural network model
Neural Networks
Learning Hierarchical Models of Scenes, Objects, and Parts
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Retrieval Properties of a Hopfield Model with Random Asymmetric Interactions
Neural Computation
Learning Overcomplete Representations
Neural Computation
Visual recognition, inference and coding using learned sparse overcomplete representations
Visual recognition, inference and coding using learned sparse overcomplete representations
A fast learning algorithm for deep belief nets
Neural Computation
Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition
International Journal of Computer Vision
Learning Sparse Overcomplete Codes for Images
Journal of VLSI Signal Processing Systems
Sparsity preserving projections with applications to face recognition
Pattern Recognition
Brain inspired cognitive system for learning and memory
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Discriminant sparse neighborhood preserving embedding for face recognition
Pattern Recognition
Heteroscedastic Sparse Representation Based Classification for Face Recognition
Neural Processing Letters
Hi-index | 0.00 |
We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and expectation-driven segmentation. Using properties of biological vision for guidance, we posit a stochastic generative world model and from it develop a simplified world model (SWM) based on a tractable variational approximation that is designed to enforce sparse coding. Recent developments in computational methods for learning overcomplete representations (Lewicki & Sejnowski, 2000; Teh, Welling, Osindero, & Hinton, 2003) suggest that overcompleteness can be useful for visual tasks, and we use an overcomplete dictionary learning algorithm (Kreutz-Delgado, et al., 2003) as a preprocessing stage to produce accurate, sparse codings of images. Inference is performed by constructing a dynamic multilayer network with feedforward, feedback, and lateral connections, which is trained to approximate the SWM. Learning is done with a variant of the back-propagation-through-time algorithm, which encourages convergence to desired states within a fixed number of iterations. Vision tasks require large networks, and to make learning efficient, we take advantage of the sparsity of each layer to update only a small subset of elements in a large weight matrix at each iteration. Experiments on a set of rotated objects demonstrate various types of visual inference and show that increasing the degree of overcompleteness improves recognition performance in difficult scenes with occluded objects in clutter.