Using linear regression for classification problems is prone to outliers
Logistic Regression using sigmoid squashing comes to the rescue.
In this video we shall understand what logistic regression is and how squashing helps us solve the challenges associated with outliers in linear regression.
We shall also learn about logloss and how it suits the problem of probabilistic outputs.
Watch the video to learn more
Video summary
00:00 - Introduction
01:00 - Agenda
02:34 - Logistic regression (Binary vs Multiclass)
04:10 - Why Linear Regression fails??
08:18 - Squashing
12:40 - logloss
21:13 - thought for the week
21:49 - Summary and Implementation
References
Summary slides: https://docs.google.com/presentation/...
squashing and its use: https://www.aitude.com/comparison-of-...
implementation: https://scikit-learn.org/stable/modul...
If you are new to the channel, make sure to subscribe and share it with your friends and data science enthusiasts :]
On this page of the site you can watch the video online Complete Logistic Regression Classifier with Python Code || Machine Learning using Scikit-learn with a duration of hours minute second in good quality, which was uploaded by the user Datahat -- Simplified AI 27 November 2022, share the link with friends and acquaintances, this video has already been watched 318 times on youtube and it was liked by 10 viewers. Enjoy your viewing!