Biomedical subjects

Shouji Sakamoto

Publications and source records attributed to Shouji Sakamoto.

2 recordsLinked to original sources

PubMedDate not supplied

Stability of generalized topographic mappings between cell layers through correlational learning.

We propose a simple topographic mapping formation model from a cell layer to a cell layer. Our model is a discrete one in that the state value of input and output cells takes 0 or 1 and input and output layers are represented by undirected graphs. A binary input pattern can be given to the network consisting of input and output cell layers. Such an input pattern can be represented by a subset of input cells. That is, a state value of an input cell takes 1 if a cell belongs to the subset, otherwise, a state value of an input cell is 0. Such a definition of an input pattern does not necessarily assume a short-range excitatory mechanism in an input layer. Thus, a topographic mapping described in this model is a map, which preserves the input pattern relation. By using the concept of input pattern separability, we showed an existence condition of certain learning rules, which are correlational. We have paid special attention to such correlational type learning rules, and have shown under the rules that topographic mappings are the only stable ones. As to the non-correlational learning rules, we also investigate the stability of generated mappings.

Algorithms↗

PubMedDate not supplied

Synaptic weight normalization effects for topographic mapping formation.

We propose a simple topographic mapping formation model between cell layers with weight normalization. In our model, each cell layer can have an arbitrary neighborhood relation between the cells represented by an undirected graph. Thus, a topographic mapping described in this model is a map which preserves the adjacency relation. We define several learning rules, input and output type weight normalization methods. Then, we not only concentrate on a Hebbean weight modification but also investigate the effects of normalization under a non-Hebbean weight modification. We first show that when an input type normalization is adopted or without normalization, a topographic mapping is stable under the correlational type learning rule, but when an output type normalization is adopted a topographic mapping is stable under not only the correlational type learning rule but also the non-correlational one. Next, we show by computer simulations that when an output type normalization is considered we have more learning rules which yield topographic mappings than the cases when an input type normalization is adopted or without normalization.

Algorithms↗