Year: 2014
Type: article
Abstract: Over the past few years, multiple kernel learning (MKL) has received significant attention among data-driven feature selection techniques in the context of kernel-based learning. MKL formulations have been devised and solved for a broad spectrum of machine learning problems, including multitask learning (MTL). Solving different MKL formulations usually involves designing algorithms that are tailored to the problem at hand, which is, typically, a nontrivial accomplishment. In this paper we present a general multitask multiple kernel learning (MT-MKL) framework that subsumes well-known MT-MKL formulations, as well as several important MKL approaches on single-task problems. We then derive a simple algorithm that can solve the unifying framework. To demonstrate the flexibility of the proposed framework, we formulate a new learning problem, namely partially-shared common space MT-MKL, and demonstrate its merits through experimentation.
Language: English
Topic: Machine Learning and ELM
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
Awards: Collaborative Research: RET in Engineering and Computer Science Site: Research Experiences for Teachers Focused on Applications of ImagEs and SiGnals In High Schools (AEGIS), Young Entrepreneur and Scholar (YES) Scholarship Program, UCF STEP Pathways to STEM: From Promise to Prominence, I3: The UCF Community Embraces the Knowledge-Based Economy, REU Sites: Collaborative Research: Advances of Machine Learning in Theory & Applications (AMALTHEA), UCF COMPASS (Convincing Outstanding-Math-Potential Admits to Succeed in STEM)
OpenAlex ID: W2122383747