Timezone: »

Kernel Methods for Deep Learning
Youngmin Cho · Lawrence Saul

Wed Dec 09 07:00 PM -- 11:59 PM (PST) @ None #None

We introduce a new family of positive-definite kernel functions that mimic the computation in large, multilayer neural nets. These kernel functions can be used in shallow architectures, such as support vector machines (SVMs), or in deep kernel-based architectures that we call multilayer kernel machines (MKMs). We evaluate SVMs and MKMs with these kernel functions on problems designed to illustrate the advantages of deep architectures. On several problems, we obtain better results than previous, leading benchmarks from both SVMs with Gaussian kernels as well as deep belief nets.

Author Information

Youngmin Cho (University of California, San Diego)
Lawrence Saul (UC San Diego)

More from the Same Authors