A generic framework for embedding human brain function with temporally correlated autoencoder

Lin Zhao, Zihao Wu, Haixing Dai, Zhengliang Liu, Xintao Hu, Tuo Zhang, Dajiang Zhu, Tianming Liu

Abstract: Highlights•A novel and generic framework for representing human brain function as embedding.•The learned embeddings are neuroscientifically meaningful and interpretable.•Learned embedding boosts the downstream task performance effectively.•Bridge the semantic gap between human brain function and artificial neural network.