Yoshikazu Nishikawa

Adaption to a Changing Environment by Means of the Thermodynamical Genetic Algorithm

In applications of the genetic algorithms (GA) to problems of adaptation to changing environments, maintenance of the diversity of the population is an essential requirement. Taking this point into consideration, the authors have proposed to utilize the thermodynamical genetic algorithm (TDGA) for the problems of adaptation to changing environments. The TDGA is a genetic algorithm that uses a selection rule inspired by the principle of the minimal free energy in thermodynamical systems. In the present paper, the authors propose a control method of the temperature, an adjustable parameter in the TDGA. The temperature is controlled by a feedback technique so as to regulate the level of the diversity of the population measured by entropy. The adaptation ability of the proposed method is confirmed by computer simulation taking time-varying knapsack problems as examples.

Reinforcement learning of dynamic behavior by using recurrent neural networks

Reinforcement learning is a learning scheme for finding the optimal policy to control a system, based on a scalar signal representing a reward or a punishment. If the observation of the system by the controller is sufficiently rich to represent the internal state of the system, the controller can achieve the optimal policy simply by learning reactive behavior. However, if the state of the controlled system cannot be assessed completely using current sensory observations, the controller must learn a dynamic behavior to achieve the optimal policy.In this paper, we propose a dynamic controller scheme which utilizes memory to uncover hidden states by using information about past system outputs, and makes control decisions using memory. This scheme integrates Q-learning, as proposed by Watkins, and recurrent neural networks of several types. It performs favorably in simulations which involve a task with hidden states.

The degree of human visual attention in the visual search

Human beings can obtain visual information in parallel through the retina, but they cannot pay attention to all the information at the same time. In psychological studies, the human characteristics of visual attention have often been investigated by analyzing the characteristics of the visual search task. Previous studies suggested that the information features of the visual search task are processed in parallel at early stages of processing. However, the authors consider that these features are not processed completely in parallel, and have a reciprocal action to each other. In order to clarify the reciprocal action of the features in a visual search and the continuity of visual attention, the characteristics of reaction times were measured with changing forms of visual stimuli. The experimental results suggested that the reaction time changed when the features of the visual stimuli in the visual search task changed. This means that the features are affected by each other. Furthermore, continuity of reciprocal action is also suggested, and the degree of visual attention is decided by this continuity. The results provided significant basic data to support our proposed mathematical model of visual attention.

A Computation Theory for Orientation-Selective Simple Cells Based on the MAP Estimation Principle and Markov Random Fields

A computation theory is proposed for the orientation-selective simple cells of the striate cortex. The theory consists of three parts: (a) a probabilistic computation theory based on MRFs and the MAP estimation principle which is assumed to be carried out by the visual pathway lying between the lateral geniculate nuclei and the simple cells; (b) a deterministic parallel algorithm which compute the MAP estimation approximately; and (c) a neural implementation of the algorithm.