Search

A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons' states in order to construct learning algorithm for this network. An error back-propagation algorithm is introduced for modifying the connection weights of the network. [ABSTRACT FROM AUTHOR]

A process of trial and error plays an important role in not only the human learning but also the machine learning. Such a process is called exploration in the reinforcement learning which has originated from experimental studies on learning in psychology. A uniform pseudorandom number generator appears to be suitable for exploration. However, it is known that a chaotic source also provides a random-like sequence as like as a stochastic source. By applying this random-like feature of a deterministic chaotic generator for exploration in a nonstationary shortcut maze problem, we have observed that a deterministic chaotic generator provides a better performance than a stochastic random exploration generator when used for exploration based on a logistic map. In this study, in order to confirm this difference in the performances of the two generators, we examine another nonstationary task – target capturing. The simulation result of this task agrees with the result of our previous study. From the view of multi-agent system, it is an inhomogeneous or heterogeneous system composed of some kinds of agents in many cases. In such situations, the exploration of them is not uniform. Chaotic exploration may suit well this heterogeneity in such a multi-agent system. [ABSTRACT FROM AUTHOR]

Associative memory networks based on quaternionic Hopfield neural network are investigated in this paper. These networks are composed of quaternionic neurons, and input, output, threshold, and connection weights are represented in quaternions, which is a class of hypercomplex number systems. The energy function of the network and the Hebbian rule for embedding patterns are introduced. The stable states and their basins are explored for the networks with three neurons and four neurons. It is clarified that there exist at most 16 stable states, called multiplet components, as the degenerated stored patterns, and each of these states has its basin in the quaternionic networks. [ABSTRACT FROM AUTHOR]

With the development of our highly information-oriented society, there is an increasing demand for large-scale and high-level information processing. Toward this goal, studies have sought to create a new computation principle having an information processing ability exceeding the existing Neumann-type computer, such as the creation of a new computation theory or the integration of the frameworks of existing computation theories. As one such approach, quantum neural computing is considered to be interesting, which integrates neural computing and quantum computation. This paper constructs the feed-forward neural network, which is widely used in practice, based on the qubit neuron model. The 4-bit parity-check problem and the general function identification problem are considered. The performance is compared to the feed-forward network based on the conventional neuron model, and it is shown that the proposed model has a higher performance than the conventional model, using the learning diagram composed of convergence rate and the number of learning iterations. The reason for the better performance is also discussed. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(13): 43–51, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10342 [ABSTRACT FROM AUTHOR]

Previously, the authors introduced a stimulus–response scheme that supports plastic variation of synapse weights in chaotic neural networks, and analyzed how memory formation evolved under external stimulation. In this paper, the same analysis is applied to stochastic neural networks with different dynamics, and the obtained results are compared to those for chaotic networks to examine the influence exerted by dynamic parameters on the memorization process. In experiments, chaotic networks proved to be more efficient than stochastic networks. This is indicative of functionality of neural chaos in stimulus–response scheme that is close to natural learning, while further experiments are required to confirm the generality of this conclusion. © 2001 Scripta Technica, Syst Comp Jpn, 32(6): 29–35, 2001 [ABSTRACT FROM AUTHOR]