His current research areas include evolutionary computation on many-core architecture and evolution of machine learning techniques in design. In particular, he mainly studies the following three.

(1) Most of real-world problems are multi-objective optimization problems involving several conflicting objectives. On the other hand, cloud systems may even offer tens of thousands of virtual machines, terabytes of memories and exa-bytes of storage capacity. Current trend toward many-core architecture increases the number of cores even more dramatically. Therefore, he is working on high-performance parallel evolutionary computation to find non-dominant solution sets (Pareto front) while maintaining solution accuracy.

(2) Currently, swarm intelligence is actively researched, but it is necessary to adjust parameters by trial and error for each test problem, which is a burden when applied to actual problems. Therefore, he is conducting swarm intelligence research to find a solution with high accuracy and no parameter adjustment for the multimodal problem.

(3) Deep learning is very effective in supervised learning in which teacher data is sufficiently prepared. On the other hand, when sufficient teacher data cannot be prepared or in reinforcement learning, it is difficult to learn accurately. Therefore, he is working for neuroevolution (neural networks structure generation and/or weights value learning using evolutionary computation) of deep neural networks. He received the 2015 Highly Commended Paper Award of IJICC. From 2007 to 2008, he was a visiting scholar at Illinois Genetic Algorithms Laboratory (IlliGAL). He is a member of the IEEE Computational Intelligence Society, the IEEE Computer Society, the ACM/SIGEVO, the Japanese Society for Evolutionary Computation, and the Information Processing Society of Japan. He is also a member of program committee of Genetic and Evolutionary Computation Conference since 1999.