A large scale neural network 'CombNET-II'
Akira Iwata, Ken-ichi HOTTA, Hiroshi Matsuo, Nobuo Suzumura · 2002
Summary form only given. The authors propose a large-scale neural network model, CombNET-II, which consists of a four-layered network with a comb structure. A vector quantizing network forms the first layer as a stem and many three-layered networks form layers two through four as branches. As input data flows into the stem network, one of the category groups is selected according to the activation level of the neuron. Then the input data flows into one of the branch networks, which classifies the input data into a specified category. CombNET-II employs a self-growing procedure for learning the stem network and back propagation for branch networks. CombNET-II was applied to implement a network to classify 2965 printed Kanji characters (Japanese Industrial Standard, JIS first-level set). Recognition rates of 99.8 approximately 99.9% have been achieved for test data sets. This network consists of more than 10000 neurons and nearly 1 million connections.>