Information Geometry and Its Applications

VSF-Network, Vibrate Synchronize Function Network, is a hybrid neural network combining a Chaos Neural Network with a hierarchical network. VSF-Network is designed for symbol learning by a neural network. It finds unknown parts of input data by comparing to learned pattern and it learns unknown patterns using unused part of the network. The new patterns are learned incrementally and they are represented as sub-networks with unused parts of hierarchical neural network. Combinations of patterns are represented as combinations of the sub-networks. The combinations of symbols are represented as combinations of the sub-networks. In this paper, the two theoretical backgrounds of VSF-Network are introduced. At the first, an incremental learning framework with Chaos Neural Networks is introduced. Next, the pattern recognition with the combined with symbols is introduced. By Stochastic Catastrophe Model, the authors explain the combined pattern recognition. Through an experiment, both the incremental learning capability and the pattern recognition with pattern combination. Index Terms: Incremental learning, Chaos Neural network, Nonlinear dynamics, Stochastic Catastrophe Model.

Vibrate Synchronize Function neural network model — Its backgrounds

VSF-Network,Vibration Synchronizing Function Network, is a hybrid neural network combining a chaos neural network with a hierarchical network. It is a neural network model which learns symbols. In this paper, the two theoretical backgrounds of VSF-Network are described. The first one is the incremental learning by CNN and the second background is ensemble learning. VSF-Network finds unknown parts of input data by comparing to learned pattern and it learns the unknown parts using unused part of the network. By the ensemble learning, the capability of VSF-network for recognizing combined patterns that are learned by every sub-network of VSF-network can be explained. Through the experiments, we show that VSF-network can recognize combined patterns only if it has learned parts of the patterns and show factors for affecting performance of the learning.

Selective connection weight update, its background and experimental considerations

In this paper, a theoretical analysis on the internal structure and learning method of VSF-Network is introduced. It is a hybrid neural network combining hierarchical neural network and the chaotic neural network. The hierarchical neural network learns patterns and recognizes patterns based on the learning results.. The chaotic neural network monitors the internal structure of the hierarchical neural network and identifies learned units and unused units. The result of this identification is used for selection of the updating target at the time of updating the weight. With this selective weight update, the hierarchical neural network of the VSF-Network is divided into subnetworks that recognize previously learned patterns and subnetworks that recognize newly learned patterns. The monitoring by chaotic neural network is explained as calculation of eigenspace of its recall process. Furthermore, it is explained from the viewpoint of the combination of the divided linear spaces that the subnetworks obtained by learning can be recognized in combination according to the situation. Finally, the validity and problems of the theoretical explanation are introduced through the analysis of the intermediate layer of VSF-Network during incremental learning.

Analysis of inner structure of VSF-Network

VSF-Network,Vibration Synchronizing Function Network, is a hybrid neural network combining a chaos neural network with a hierarchical network. It is a neural network model which learns symbols. In this paper, the two theoretical backgrounds of VSF---Network are described. The first one is the incremental learning by CNN and the second background is ensemble learning. VSF-Network finds unknown parts of input data by comparing to learned pattern and it learns the unknown parts using unused part of the network. By the ensemble learning, the capability of VSF-network for recognizing combined patterns that are learned by every sub-network of VSF-network can be explained. Through the experiments, we show that VSF-network can recognize combined patterns only if it has learned parts of the patterns and show factors for affecting performance of the learning.

Yoshitsugu Kakemoto

Papers

Vibrate Synchronize Function neural network model — Its backgrounds

Selective connection weight update, its background and experimental considerations

Analysis of inner structure of VSF-Network

Selective weight update rule for hybrid neural network