Naoki Masuyama

Application of emotion affected associative memory based on mood congruency effects for a humanoid

Emotional factor plays an important role in communication. In the field of psychology, it is known that memory and emotions are closely related to each other. In this paper, we present the significance of emotional factors to associative memory in communication and apply it on human–robot interaction problems. Emotional models for the robot partner are developed, and an interactive robot system with a complex-valued multi-directional associative memory model is proposed. We utilize multi-modal information such as object, gesture, voice, and facial expressions to associate the relationships in associative memory, and generate the emotional information for the robot partner. As a result, the robot partner is able to perform various actions depending on the emotional factors. Results from the interactive experiments indicate possibility of suitable information for communication space being provided from the robot partner.

Personality affected robotic emotional model with associative memory for human-robot interaction

The decision making process in communication is affected by internal and external factors from dynamic environments. Humans can perform a variety of behaviors in a similar situation, unlike robots. This paper discusses human psychological phenomena during communication from the point of view of internal and external factors, such as perception, memory, and emotional information. Based on these, we introduce the personality affected robotic emotional model and the emotion affected associative memory model for the robot. We organize an interactive robot system to provide suitable decisions for the robot. Results from interactive communication experiments indicate that the robot is able to perform different actions based on internal and external factors.

Quantum-Inspired Complex-Valued Multidirectional Associative Memory

Complex-valued neuron is one of the significant and effective innovation in artificial neural networks. It is able to deal with multi-valued pattern and oscillator models. With regard as associative memory, several types of complex-valued artificial neural associative memories have developed, and confirmed its superior abilities. Conventionally, we have developed Quantum-Inspired Mulitidirectional Associative Memory (QMAM). This model demonstrates quantum information processing in neural structures results in an exponential increase in storage capacity and can explain the extensive memory and inferencing capabilities of humans. This model is applied a fuzzy inference to weight matrix to satisfy parallelism and unitarity. In this paper, we introduce Quantum-Inspired Complex-Valued Multidirectional Associative Memory (QCMAM) to handle multi-valued information. In addition, the mathematical proofs of parallelism and unitarity for a complex-valued model are presented. The simulation experiments show that QCMAM has superior abilities comparing with conventional model.

Affective communication robot partners using associative memory with mood congruency effects

Associative memory is one of the significant and effective functions in communication. Conventionally, several types of artificial associative memory models have been de-veloped. In the field of psychology, it is known that human memory and emotions are closely related each other, such as the mood-congruency effects. In addition, emotions are sensitive to sympathy for facial expressions of communication partners. In this paper, we develop the emotional models for the robot partners, and propose an interactive robot system with a complex-valued bidirectional associative memory model that associations are affected by emotional factors. We utilize multi-modal information such as gesture and facial expressions to generate emotional factors. The results of interactive communication experiment show that there is a possibility to provide the suitable information for the interactive space.

Computational intelligence for human interactive communication of robot partners

This paper proposes a multi-modal communication method for human-friendly robot partners based on various types of sensors. We explain informationally structured space to extend the cognitive capabilities of robot partners based on environmental systems. We propose an integration method for estimating human behaviors using sound source angle information, and gesture recognition by the multi-layered spiking neural network with the time series of human hand positions. Finally, we show several experimental results of the proposed method, and discuss the future direction on this research.

Use of Two Reference Points in Hypervolume-Based Evolutionary Multiobjective Optimization Algorithms

Recently it was reported that the location of a reference point has a dominant effect on the optimal distribution of solutions for hypervolume maximization when multiobjective problems have inverted triangular Pareto fronts. This implies that the use of an appropriate reference point is indispensable when hypervolume-based EMO (evolutionary multiobjective optimization) algorithms are applied to such a problem. However, its appropriate reference point specification is difficult since it depends on various factors such as the shape of the Pareto front (e.g., triangular, inverted triangular), its curvature property (e.g., linear, convex, concave), the population size, and the number of objectives. To avoid this difficulty, we propose an idea of using two reference points: one is the nadir point, and the other is a point far away from the Pareto front. In this paper, first we demonstrate that the effect of the reference point is strongly problem-dependent. Next we propose an idea of using two reference points and its simple implementation. Then we examine the effectiveness of the proposed idea by comparing two hypervolume-based EMO algorithms: one with a single reference point and the other with two reference points.

A Double-Niched Evolutionary Algorithm and Its Behavior on Polygon-Based Problems

Multi-modal multi-objective optimization problems are commonly seen in real-world applications. However, most existing researches focus on solving multi-objective optimization problems without multi-modal property or multi-modal optimization problems with single objective. In this paper, we propose a double-niched evolutionary algorithm for multi-modal multi-objective optimization. The proposed algorithm employs a niche sharing method to diversify the solution set in both the objective and decision spaces. We examine the behaviors of the proposed algorithm and its two variants as well as three other existing evolutionary optimizers on three types of polygon-based problems. Our experimental results suggest that the proposed algorithm is able to find multiple Pareto optimal solution sets in the decision space, even if the diversity requirements in the objective and decision spaces are inconsistent or there exist local optimal areas in the decision space.

Improving 1by1EA to Handle Various Shapes of Pareto Fronts.

1by1EA is a competitive method among existing many-objective evolutionary algorithms. However, we find that it may fail to find boundary solutions depending on the Pareto front shape. In this study, we present an improved version of 1by1EA, named 1by1EA-II, to enhance the flexibility in handling various shapes of Pareto fronts. In 1by1EA-II, the Chebyshev distances from a solution to the nadir and ideal points are alternately employed as two convergence indicators. Using the first convergence indicator, boundary solutions are preferred for a wide spread in the objective space. With the other convergence indicator, non-boundary solutions are preferred to promote diversity. We empirically compare the proposed 1by1EA-II with its original version as well as four other state-of-the-art algorithms on DTLZ and Minus-DTLZ test problems. The results show that 1by1EA-II is the most flexible algorithm.

Analysis of evolutionary multi-tasking as an island model

Recently, an idea of evolutionary multi-tasking has been proposed and applied to various types of optimization problems. The basic idea of evolutionary multi-tasking is to simultaneously solve multiple optimization problems (i.e., tasks) in a cooperative manner by a single run of an evolutionary algorithm. For this purpose, each individual in a population has its own task. This means that a population of individuals can be viewed as being divided into multiple sub-populations. The number of sub-populations is the same as the number of tasks to be solved. In this paper, first we explain that a multi-factorial evolutionary algorithm (MFEA), which is a representative algorithm of evolutionary multi-tasking, can be viewed as a special island model. MFEA has the following two features: (i) Crossover is performed not only within an island but also between islands, and (ii) no migration is performed between islands. Information of individuals in one island is transferred to another island through inter-island crossover. Next, we propose a simple implementation of evolutionary multi-tasking in the framework of the standard island model. Then, we compare our island model with MFEA through computational experiments. Promising results are obtained by our implementation of evolutionary multi-tasking.

Dual-grid model of MOEA/D for evolutionary constrained multiobjective optimization

A promising idea for evolutionary constrained optimization is to efficiently utilize not only feasible solutions (feasible individuals) but also infeasible ones. In this paper, we propose a simple implementation of this idea in MOEA/D. In the proposed method, MOEA/D has two grids of weight vectors. One is used for maintaining the main population as in the standard MOEA/D. In the main population, feasible solutions always have higher fitness than infeasible ones. Among infeasible solutions, solutions with smaller constraint violations have higher fitness. The other grid is for maintaining a secondary population where non-dominated solutions with respect to scalarizing function values and constraint violations are stored. More specifically, a single non-dominated solution with respect to the scalarizing function and the total constraint violation is stored for each weight vector. A new solution is generated from a pair of neighboring solutions in the two grids. That is, there exist three possible combinations of two parents: both from the main population, both from the secondary population, and each from each population. The proposed MOEA/D variant is compared with the standard MOEA/D and other evolutionary algorithms for constrained multiobjective optimization through computational experiments.