Neural Generalization of Multiple Kernel Learning

TL;DR

This paper introduces NGMKL, a neural network extension of traditional MKL, which enhances complexity and recognition accuracy by incorporating multiple layers and nonlinear activations.

Contribution

It presents a novel neural generalization of MKL, bridging kernel methods and deep learning for improved performance.

Findings

NGMKL outperforms traditional MKL in recognition accuracy.

The method increases the complexity of MKL algorithms.

Experiments on benchmarks validate the effectiveness of NGMKL.

Abstract

Multiple Kernel Learning is a conventional way to learn the kernel function in kernel-based methods. MKL algorithms enhance the performance of kernel methods. However, these methods have a lower complexity compared to deep learning models and are inferior to these models in terms of recognition accuracy. Deep learning models can learn complex functions by applying nonlinear transformations to data through several layers. In this paper, we show that a typical MKL algorithm can be interpreted as a one-layer neural network with linear activation functions. By this interpretation, we propose a Neural Generalization of Multiple Kernel Learning (NGMKL), which extends the conventional multiple kernel learning framework to a multi-layer neural network with nonlinear activation functions. Our experiments on several benchmarks show that the proposed method improves the complexity of MKL algorithms and leads to higher recognition accuracy.