Recurrent and Concurrent Neural Networks for Objects Recognition

A system based on a neural network framework is considered. We used two neural networks, an Elman network [1][2] and a Kohonen (concurrent) network [3], for a categorization task. The input of the system are objects derived from three general prototypes: circle, square, polygon. We varied the size and orientation of the objects in a continuous way. The system is trained using a new algorithm, based on recurrent version of backpropagation and Kohonen rule. The system achieves the capacity to predict the shape of the objects with a remarkable generalization [4]. We compare our results with the results using a classical Elman network. The model is implemented by a Matlab/Simulink environment. KEY WORDS Artificial neural networks; recurrent neural networks; object recognition; artificial vision; autonomous robotics.

• Type: Conference
• Year: 2006
• Where: AIA
• Authors: Federico Cecconi, Marco Campenní
• Keywords: AIA 2006, AIA 2007, Elman Network, Neural Network Framework, Neural Networks