Yuko Osana

Learn More
—In this paper, we propose a chaotic complex-valued associative memory which can realize a dynamic association of multi-valued patterns. The proposed model is based on a complex-valued associative memory and a chaotic associative memory. The complex-valued asso-ciative memory can treat multi-valued patterns, and the chaotic associative memory can recall(More)
In this paper, we propose a successive learning method in hetero-associative memories, such as Bidirectional Associative Memories and Multidirectional Associative Memories, using chaotic neural networks. It can distinguish unknown data from the stored known data and can learn the unknown data successively. The proposed model makes use of the difference in(More)
The neuronal network of the soil nematode Caenorhabditis elegans (C. elegans), which is a good prototype for biological studies, is investigated. Here, the neuronal network is simpliÿed as a graph. We use three indicators to characterize the graph; vertex degree, generalized eccentricity (GE), and complete subgraphs. The graph has the central part and the(More)
—In this paper, we propose a Kohonen feature map associative memory with area representation for sequential patterns. This model is based on the Kohonen feature map associative memory with area representation and the Kohonen feature map associative memory for temporal sequences. The proposed model can learn sequential patterns successively, and has(More)