Guest Editorial: Special issue on machine learning and deep learning algorithms for complex networks

[摘要] In the latest years, researchers from the industry and academiaextensively applied machine learning algorithms in a broadrange of domains. The goal of this special issue is to illustratethe most recent applications of deep learning methods in arange of real‐life domains and to show the practical utility ofthese techniques. A particular attention goes towards methodsto process network data that is capable of modelling complexartificial and natural systems as the interactions of a multitudeof simpler entities.The first paper of this special issue is by Du et al., whichdeals with an intriguing (and quite unexplored researchquestion): can we use deep neural networks to make timeseries prediction? The authors combine a well‐known statistical model called State Space Model (SSM) with deepneural networks to obtain a time series forecasting modelcalled Deep Nonlinear State Space Model (DNLSSM). Theirexperimental results show the superiority of DNLSSMagainst a broad range of competitors on both real andsynthetic datasets.

[学科分类] 数学（综合）