Generating an SVM Kernel function using genetic algorithm

• Main Author: IMMER, BALDOS
• Format: text
• Published: Archīum Ateneo 2012
• Subjects: Support vector machines; Supervised learning (Machine learning)Kernel functions
• Online Access: https://archium.ateneo.edu/theses-dissertations/192
• Institution: Ateneo De Manila University

SVMs' performance is affected greatly by the choice of kernel function and kernel parameters. This study made use of a complete binary tree of depth 3 and the Genetic Algorithm to automate the non-trivial task of finding a kernel function that best classi