In this paper, we propose a multi-kernel multi-view canonical correlations(M2CCs) framework for subspace learning. In the proposed framework,the input data of each original view are mapped into multiple higher dimensi...In this paper, we propose a multi-kernel multi-view canonical correlations(M2CCs) framework for subspace learning. In the proposed framework,the input data of each original view are mapped into multiple higher dimensional feature spaces by multiple nonlinear mappings determined by different kernels. This makes M2 CC can discover multiple kinds of useful information of each original view in the feature spaces. With the framework, we further provide a specific multi-view feature learning method based on direct summation kernel strategy and its regularized version. The experimental results in visual recognition tasks demonstrate the effectiveness and robustness of the proposed method.展开更多
Deviations from bulk morphologies in thin films of binary blends of alkyne-functionalized diblock copolymer poly（ethylene oxide）-bloek-poly（n-butyl methacrylate-random-propargyl methacrylate） （PEO-b-P（nBMA-r-PgM...Deviations from bulk morphologies in thin films of binary blends of alkyne-functionalized diblock copolymer poly（ethylene oxide）-bloek-poly（n-butyl methacrylate-random-propargyl methacrylate） （PEO-b-P（nBMA-r-PgMA）） and Rhodamine B azide are reported, where thermal click reaction between the two components leads to microphase separated morphologies. Both in the bulk and in thin films, increasing the azide loading ratio resulted in the u＇ansition from a lamellar microdomain morphology to a hexagonally packed cylindrical mireodomain morphology. However, in thin films the lamellae-cylinder transition was observed at a different azide loading ratio, which was determined by film thickness. As a result, significant deviations from the bulk morphology were observed. These results indicate that surface interactions and confined geometry can play an important role in dictating the morphology in thin films of BCP/additive binary blends.展开更多
基金supported by the National Natural Science Foundation of China under Grant Nos. 61402203, 61273251, and 61170120the Fundamental Research Funds for the Central Universities under Grant No. JUSRP11458the Program for New Century Excellent Talents in University under Grant No. NCET-12-0881
文摘In this paper, we propose a multi-kernel multi-view canonical correlations(M2CCs) framework for subspace learning. In the proposed framework,the input data of each original view are mapped into multiple higher dimensional feature spaces by multiple nonlinear mappings determined by different kernels. This makes M2 CC can discover multiple kinds of useful information of each original view in the feature spaces. With the framework, we further provide a specific multi-view feature learning method based on direct summation kernel strategy and its regularized version. The experimental results in visual recognition tasks demonstrate the effectiveness and robustness of the proposed method.
基金supported by the Department of Energy Office of Basic Energy Science under Contract No. DE-FG02-96ER45612(XW, TPR design of experiments, synthesis of BCP)the NSF-supported Materials Research Science and Engineering Center and the NSF-supported Center for Hierarchical Manufacturing at University of Massachusetts Amherst(XS, WG, assistance with the GISAXS measurements)+1 种基金Use of the Advanced Photon Source, an Office of Science User Facility operated for the U.S.Department of Energy Office of Science by Argonne National Laboratory, was supported by the U.S. DOE under Contract No. DE-AC02-06CH11357Use of the Advanced Light Source is supported by the Director Office of Science, Office of Basic Energy Sciences, of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231
文摘Deviations from bulk morphologies in thin films of binary blends of alkyne-functionalized diblock copolymer poly（ethylene oxide）-bloek-poly（n-butyl methacrylate-random-propargyl methacrylate） （PEO-b-P（nBMA-r-PgMA）） and Rhodamine B azide are reported, where thermal click reaction between the two components leads to microphase separated morphologies. Both in the bulk and in thin films, increasing the azide loading ratio resulted in the u＇ansition from a lamellar microdomain morphology to a hexagonally packed cylindrical mireodomain morphology. However, in thin films the lamellae-cylinder transition was observed at a different azide loading ratio, which was determined by film thickness. As a result, significant deviations from the bulk morphology were observed. These results indicate that surface interactions and confined geometry can play an important role in dictating the morphology in thin films of BCP/additive binary blends.
