"Brain-inspired multimodal learning based on neural networks" by Chang Liu, Fuchun Sun et al.

Article Title

Brain-inspired multimodal learning based on neural networks

Authors

Chang Liu, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Fuchun Sun, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
Bo Zhang, Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

Keywords

multimodal learning, brain-inspired learning, deep learning, neural networks

Abstract

Modern computational models have leveraged biological advances in human brain research. This study addresses the problem of multimodal learning with the help of brain-inspired models. Specifically, a unified multimodal learning architecture is proposed based on deep neural networks, which are inspired by the biology of the visual cortex of the human brain. This unified framework is validated by two practical multimodal learning tasks: image captioning, involving visual and natural language signals, and visual-haptic fusion, involving haptic and visual signals. Extensive experiments are conducted under the framework, and competitive results are achieved.