Cultural inheritance through Swarm intelligence learning

Cultural inheritance is the main factor for the evolution and skills development through generations. This paper exploits two Machine Learning techniques to imitate the learning process that constitutes the cultural inheritance of Elephants in a Swarm Intelligence (SI) algorithm called the Robotic-Elephant Herding Optimization (REHO). The first REHO-based learning utilizes a GPU k- Nearest Neighbors (GPU-kNN) algorithm, while the second is based on a Deep Neural Network. The performances of the Machine Learning (ML) algorithms are evaluated through five well-known metrics. Their effectiveness in solving the Target Detection Problem is compared with the original REHO via several experiments. The results show that the Deep Learning (DL) model performs better than the GPU-KNN method. These findings prompted us to propose a new hybrid SI and DL model algorithm, namely Robotic-Elephant and Particle Cultural Algorithm (REPCA). This novel approach combines the strength of the REHO-based learning model with the dynamic velocity accelerator of Particle Swarm Optimization (PSO) and knowledge inheritance provided by the Cultural Algorithm. The application problem consists of a swarm of robots that cooperate to detect an exponentially increasing number of targets, known as the Dynamic Target Detection Problem (DTDP). The proposed REPCA is compared with up-to-date algorithms on recent and real-world applications covering the robotics field and the Covid-19 pandemic. The results show a significant positive impact that the cultural inheritance and hybrid methods bring to solve the DTDP.