Visual Recognition and Inference Using Dynamic Overcomplete Sparse Learning

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 and Sejnowski, 2000; Teh et al., 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 ...

• Type: Journal
• Year: 2007
• Where: NECO
• Authors: Joseph F. Murray, Kenneth Kreutz-Delgado
• Keywords: Et Al, NECO 2007, Visual Inference, World Model