چکیده

Machine learning (ML) refers to a set of numerous methods and algorithms which build the models based on the past, known as observed data, in order to classify, predict and make decisions. In the other word, a model is built through the training data and then it is able to recognize the new one. According to the kind of the input and feedback, ML methods are divided into four main categories such as supervised learning, unsupervised learning, reinforcement learning and deep learning. Each one includes the various tools with their different corresponding applications. For example, in precision Medicine, to diagnose malignant and benign cancers based on the size of tumor; to make automated personalized insulin pumps (artificial pancreas) in order to control the blood sugar, are among the applications of ML with different tools. One of the tools in supervised learning for classification is support vector machine (SVM) where in an inner product space, we explore a hyperplane via optimization. Since usually, finding a linear classifier is not possible, we map the points to higher dimensional feature space. Furthermore, to reduce the computations, we use a kernel instead of the feature map. In this work, we present a variety of motivation examples for applied and theoretical purposes of ML tools, in particular SVM. Moreover, we review the definition of kernel in Hilbert space and how to build new types such as polynomials and Gaussian families. Finally, we study a generic definition and framework of construction of reproducing kernel Hilbert spaces.

کليدواژه ها

Machine learning, support vector machine, feature map, reproducing kernel Hilbert spaces

کد مقاله / لینک ثابت به این مقاله

برای لینک دهی به این مقاله، می توانید از لینک زیر استفاده نمایید. این لینک همیشه ثابت است :

نحوه استناد به مقاله

در صورتی که می خواهید در اثر پژوهشی خود به این مقاله ارجاع دهید، به سادگی می توانید از عبارت زیر در بخش منابع و مراجع استفاده نمایید:
مقداد میرابراهیمی , 1400 , بررسی کرنل ها در فضای هیلبرت با هدف کاربردی در یادگیری ماشین , نخستین همایش بین المللی و سومین همایش ملی ریاضیات زیستی