Overview
This course provides an introduction to Support Vector Machines (SVMs) with a focus on visual understanding, requiring minimal math background. The learning outcomes include understanding the classification goal of splitting data, learning about the Perceptron algorithm, SVM classification errors, margin errors, and the impact of the C parameter. The course teaches skills such as data classification, error analysis, and parameter tuning. The teaching method involves visual explanations and examples. The intended audience for this course is beginners in machine learning or individuals looking to understand SVMs without a strong mathematical background.
Syllabus
Introduction
Classification goal: split data
Perceptron algorithm
Split data - separate lines
How to separate lines?
Expanding rate
Perceptron Error
SVM Classification Error
Margin Error
Challenge - Gradient Descent
Which line is better?
The C parameter
Series of 3 videos
Thank you!
Taught by
Serrano.Academy