With the wide deployments of heterogeneous networks, huge amounts of data with characteristics of high volume, high variety, high velocity, and high veracity are generated. These data, referred to multimodal big data, contain abundant intermodality and cross-modality information and pose vast challenges on traditional data fusion methods. In this review, we present some pioneering deep learning models to fuse these multimodal big data. With the increasing exploration of the multimodal big data, there are still some challenges to be addressed. Thus, this review presents a survey on deep learning for multimodal data fusion to provide readers, regardless of their original community, with the fundamentals of multimodal deep learning fusion method and to motivate new multimodal data fusion techniques of deep learning. Specifically, representative architectures that are widely used are summarized as fundamental to the understanding of multimodal deep learning. Then the current pioneering multimodal data fusion deep learning models are summarized. Finally, some challenges and future topics of multimodal data fusion deep learning models are described.

The development of control technology for the brain is of potential significance to the prevention and treatment of neuropsychiatric disorders and the improvement of humans’ mental health. A controllability analysis of the brain is necessary to ensure the feasibility of the brain control. In this letter, we investigate the influences of dynamical parameters on the controllability in the neural mass model by using controllability indices as quantitative indicators. The indices are obtained by computing Lie brackets and condition numbers of the system model. We show how controllability changes with important parameters of our dynamical (neuronal) model. Our results suggest that the underlying dynamical parameters have certain ranges with better controllability. We hope it can play potential roles in therapy for brain nervous disorder disease.