Object classifiction with recurrent feedback neural networks
Tsvi Achler · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2007
We present a mathematical model of interacting neuron- like units that we call Recurrent Feedback Neuronal Networks (RFNN). Our model is closer to biological neural networks than current approaches (e.g. Layered Neural Networks, Perceptron, etc.). Classification and reasoning in RFNN are accomplished by an iterative algorithm, and learning changes only structure (weights are fixed in RFNN). Thus it emphasizes network structure over edge weights. RFNNs are more flexible and scalable than previous approaches. In particular, integration of a new node can affect the outcome of existing nodes without modifying their prior structure. RFNN can produce informative responses to partial inputs or when the networks are extended to other tasks. It also enables recognition of complex entities (e.g. images) from parts. This new model is promising for future contributions to integrated human-level intelligent applications due to its flexibility, dynamics and structural similarity to natural neuronal networks.