MultiK-MHKS: A novel multiple kernel learning algorithm

作者：Wang Zhe; Chen Songcan; Sun Tingkai

来源：IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2): 348-353.

DOI：10.1109/TPAMI.2007.70786

• multiple kernel learning
• canonical correlation analysis
• regularization learning
• modified Ho-Kashyap algorithm
• single learning process
• pattern recognition

In this paper, we develop a new effective multiple kernel learning algorithm. First, we map the input data into m different feature spaces by m empirical kernels, where each generated feature space is taken as one view of the input space. Then, through borrowing the motivating argument from Canonical Correlation Analysis (CCA) that can maximally correlate the m views in the transformed coordinates, we introduce a special term called Inter-Function Similarity Loss R(IFSL) into the existing regularization framework so as to guarantee the agreement of multiview outputs. In implementation, we select the Modification of Ho-Kashyap algorithm with Squared approximation of the misclassification errors (MHKS) as the incorporated paradigm and the experimental results on benchmark data sets demonstrate the feasibility and effectiveness of the proposed algorithm named MultiK-MHKS.

• 出版日期2008-2
• 单位南京航空航天大学; 南京理工大学