Scalable Hybrid Deep Neural Kernel Networks

The best of two worlds:

We introduced a hybrid deep neural kernel framework. The proposed deep learning model follows a combination of neural networks based architecture and a kernel based model. In particular, here an explicit feature map is used to make the transition between the two architectures more straight-forward as well as making the model scalable to large datasets by solving the optimization problem in the primal. Experimental results show a significant improvement over shallow models on several medium to large scale real-life datasets.

For more information feel free to consult with our paper:

S. Mehrkanoon, A. Zell, J.A.K. Suykens, “Scalable Hybrid Deep Neural Kernel Networks”, in Proc. of the 25th European Symposium on Artificial Neural Networks (ESANN), Apr. 2017, Bruges, Belgium, pp. 17-22.