Unsupervised MKL in Multi-layer Kernel Machines
This work addresses representation quality for kernel-based deep learning, but it is incremental as it extends existing methods with MKL.
The paper tackles the problem of improving representation learning in multi-layer kernel machines by introducing multiple kernel learning (MKL) in an unsupervised manner, resulting in better classifier performance on noisy MNIST datasets.
Kernel based Deep Learning using multi-layer kernel machines(MKMs) was proposed by Y.Cho and L.K. Saul in \cite{saul}. In MKMs they used only one kernel(arc-cosine kernel) at a layer for the kernel PCA-based feature extraction. We propose to use multiple kernels in each layer by taking a convex combination of many kernels following an unsupervised learning strategy. Empirical study is conducted on \textit{mnist-back-rand}, \textit{mnist-back-image} and \textit{mnist-rot-back-image} datasets generated by adding random noise in the image background of MNIST dataset. Experimental results indicate that using MKL in MKMs earns a better representation of the raw data and improves the classifier performance.