System Neural Network: Evolution and Change Based Structure Learning
Animesh Chaturvedi, Aruna Tiwari, Shubhangi Chaturvedi, Píetro Lió · IEEE Transactions on Artificial Intelligence · 2022
System evolution analytics with artificial neural networks is a challenging and path-breaking direction, which could ease intelligent processes for systems that evolve over time. In this article, we contribute an approach to doEvolution and Change Learning(ECL), which uses an evolution representor and forms aSystem Neural Network(SysNN). We proposed an algorithmSystem Structure Learning, which is divided in two steps. First step uses the evolution representor as anEvolving Design Structure Matrix(EDSM) for intelligent design learning. Second step uses aDeep Evolution Learnerthat learns from evolution and changes patterns of an EDSM to generate Deep SysNN. The result demonstrates application of the proposed approach to analyze four real-world system domains: software, natural-language, retail market, and movie genre. We achieved significant learning over highly imbalanced datasets. The learning from previous states formed SysNN as a feed-forward neural network, and then memorized information as an output matrix to recommend entity-connections.