ℓ2,1−ℓ1 regularized nonlinear multi-task representation learning based cognitive performance prediction of Alzheimer’s disease
作者：
Highlights：
• A nonlinearity-aware multi-kernel based multi-task learning is proposed.
• An efficient optimization algorithm is derived to solve the formulation.
• Experimental results demonstrate significant performance improvements over the existing methods.
• Our method is able to discover the biomarkers relevant to cognitive performance and fuse the multi-modality data.
摘要
•A nonlinearity-aware multi-kernel based multi-task learning is proposed.•An efficient optimization algorithm is derived to solve the formulation.•Experimental results demonstrate significant performance improvements over the existing methods.•Our method is able to discover the biomarkers relevant to cognitive performance and fuse the multi-modality data.
论文关键词：Alzheimer’S disease,Regression,Sparse learning,Multi-task learning,Kernel method
论文评审过程：Received 12 August 2017, Revised 18 November 2017, Accepted 24 January 2018, Available online 2 February 2018, Version of Record 16 February 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.01.028
