• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.1
• /
• pp.33-44
• /
• 2012

A class of recurrent neural networks is proposed and proven to be capable of identifying any discrete-time dynamical system. The applications of the proposed network are addressed in the encoding, identification, and extraction of finite state automata. Simulation results show that the identification of finite state automata using the proposed network, trained by the hybrid greedy simulated annealing with a modified error function in the learning stage, exhibits generally better performance than other conventional identification schemes.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3864-3877
• /
• 2022

We propose a new approach called PESA (Prioritized replay Evolutionary and Swarm Algorithms) combining prioritized replay of reinforcement learning with hybrid evolutionary algorithms. PESA hybridizes different evolutionary and swarm algorithms such as particle swarm optimization, evolution strategies, simulated annealing, and differential evolution, with a modular approach to account for other algorithms. PESA hybridizes three algorithms by storing their solutions in a shared replay memory, then applying prioritized replay to redistribute data between the integral algorithms in frequent form based on their fitness and priority values, which significantly enhances sample diversity and algorithm exploration. Additionally, greedy replay is used implicitly to improve PESA exploitation close to the end of evolution. PESA features in balancing exploration and exploitation during search and the parallel computing result in an agnostic excellent performance over a wide range of experiments and problems presented in this work. PESA also shows very good scalability with number of processors in solving an expensive problem of optimizing nuclear fuel in nuclear power plants. PESA's competitive performance and modularity over all experiments allow it to join the family of evolutionary algorithms as a new hybrid algorithm; unleashing the power of parallel computing for expensive optimization.