TY - GEN
T1 - A deep learning approach to multiple kernel fusion
AU - Song, Huan
AU - Thiagarajan, Jayaraman J.
AU - Sattigeri, Prasanna
AU - Ramamurthy, Karthikeyan Natesan
AU - Spanias, Andreas
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/6/16
Y1 - 2017/6/16
N2 - Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an alternative approach that creates dense embeddings for data using the kernel similarities and adopts a deep neural network architecture for fusing the embeddings. In order to improve the effectiveness of this network, we introduce the kernel dropout regularization strategy coupled with the use of an expanded set of composition kernels. Experiment results on a real-world activity recognition dataset show that the proposed architecture is effective in fusing kernels and achieves state-of-the-art performance.
AB - Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an alternative approach that creates dense embeddings for data using the kernel similarities and adopts a deep neural network architecture for fusing the embeddings. In order to improve the effectiveness of this network, we introduce the kernel dropout regularization strategy coupled with the use of an expanded set of composition kernels. Experiment results on a real-world activity recognition dataset show that the proposed architecture is effective in fusing kernels and achieves state-of-the-art performance.
KW - Activity recognition
KW - Deep learning
KW - Dropout regularization
KW - Kernel fusion
UR - http://www.scopus.com/inward/record.url?scp=85023770195&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85023770195&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2017.7952565
DO - 10.1109/ICASSP.2017.7952565
M3 - Conference contribution
AN - SCOPUS:85023770195
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 2292
EP - 2296
BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Y2 - 5 March 2017 through 9 March 2017
ER -