An optimization approach to achieve unsupervised segmentation and binding in a dynamical network

— We present a novel network of oscillatory units, whose behavior is described by the amplitude and phase of oscillations. While building on previous work, the system presented in this paper significantly improves existing formulations by simplifying the network architecture required, presents a simple objective function to understand the system behavior, and demonstrates the ability to solve deconvolution and segmentation problems in an unsupervised manner. We derive the network dynamics from an objective function that rewards both the faithfulness and the sparseness of representation. The resulting network architecture is simple, and the dynamics are straightforward to interpret. This network functions in an unsupervised manner, and is able to form unique representations for a set of inputs. Once the set of inputs is learnt, the network can deconvolve mixtures of inputs. A significant capability of the network is that it segments its inputs into components that most contribute to...

• Type: Conference
• Year: 2006
• Where: IJCNN
• Authors: A. Ravishankar Rao, Guillermo A. Cecchi, Charles C. Peck, James Kozloski
• Keywords: IJCNN 2006, Network Architecture, Network Dynamics, Unsupervised Manner