Neocognitron-Type Network for Recognizing Rotated and Shifted Patterns with Reduction of Resources
- First Online:
- Cite this paper as:
- Satoh S., Miyake S., Aso H. (2001) Neocognitron-Type Network for Recognizing Rotated and Shifted Patterns with Reduction of Resources. In: Mira J., Prieto A. (eds) Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. IWANN 2001. Lecture Notes in Computer Science, vol 2084. Springer, Berlin, Heidelberg
A rotation-invariant neocognitron was proposed by authors for recognition of rotated patterns. In this paper, we propose a new network in order to reduce the number of cells for the same purpose. The new network is based on the rotation-invariant neocognitron in its structure and based on an idea of hypothesis and its verification in its process. In the proposed model the following two processes are executed: 1) making a hypothesis of an angular shift of an input supported by an associative recall network and 2) verification of the hypothesis realized by mental rotation of the input. Computer simulations show that 1) the new network needs less cells than the original rotation-invariant neocognitron and 2) the difference of recognition rates between the proposed network and the original network is very little.
Keywordsrotation invariant neocognitron the number of cells associative recall mental rotation hypothesis and verification
Unable to display preview. Download preview PDF.