Metaheuristic optimisation methods have emerged as powerful tools to complement gradient-based training in deep learning. By emulating natural or social phenomena, techniques such as particle swarm ...

General approach for combining modular metaheuristic software frameworks and automatic configuration tools. To discourage the inefficient manual invention and configuration of new metaheuristic ...

Global optimization problems where evaluation of the objective function is an expensive operation arise frequently in engineering, machine learning, decision making, statistics, optimal control, etc.