Automatic deep sparse clustering with a dynamic population-based evolutionary algorithm using reinforcement learning and transfer learning

Parham Hadikhani, Daphne Teck Ching Lai, Wee-Hong Ong, Mohammad H. Nadimi-Shahraki

Abstract: Highlights•Introduces a novel clustering method integrating Auto-Encoders, Evolutionary Algorithms, and Reinforcement Learning.•Adjusts population size and strategy dynamically with Reinforcement Learning to enhance exploration.•Uses Generative Adversarial Networks to share elite populations among strategies, boosting diversity and solution quality.•Addresses feature extraction inefficiencies and local optima issues through dynamic, adaptive techniques.•Outperforms existing methods and works effectively without needing prior knowledge of the number of clusters.

External IDs:dblp:journals/ivc/HadikhaniLON24