Local Rademacher Complexity Machine
| Autor: | Sandro Ridella, Luca Oneto, Davide Anguita |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer Science::Machine Learning
0209 industrial biotechnology Series (mathematics) business.industry Computer science Cognitive Neuroscience Transposition (telecommunications) Kernel methods Local Rademacher Complexity Theory 02 engineering and technology Local Rademacher Complexity Machine Computer Science Applications Support vector machine Statistics::Machine Learning 020901 industrial engineering & automation Artificial Intelligence Support Vector Machines Vapnik–Chervonenkis Theory Rademacher complexity 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | Scopus-Elsevier |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2018.10.087 |
| Popis: | Support Vector Machines (SVMs) are a state-of-the-art and powerful learning algorithm that can effectively solve many real world problems. SVMs are the transposition of the Vapnik–Chervonenkis (VC) theory into a learning algorithm. In this paper, we present the Local Rademacher Complexity Machine (LRCM), a transposition of the Local Rademacher Complexity (LRC) theory, the state-of-the-art evolution of the VC theory, into a learning algorithm. Analogously to what has been done for the SVMs, we will present first the theoretical ideas behind the LRC theory, we will show how these ideas can be translated into a learning algorithm, the LRCM, and then how the LRCM can be made efficient and kernelizable. By exploiting a series of real world datasets, we will show the effectiveness of the LRCM against the SVMs. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect