From the course: Machine Learning in Telecommunication: From Basics to Real-World Cases
Unlock this course with a free trial
Join today to access over 24,800 courses taught by industry experts.
Using hypothesis testing to predict network performance
From the course: Machine Learning in Telecommunication: From Basics to Real-World Cases
Using hypothesis testing to predict network performance
(gentle music) - [Instructor] Have you ever wondered how businesses predict things like sales or in networks, how we are predicting throughput based on some input factors? What if there was a way to mathematically predict outcomes based on past data? Well, that's exactly we are going to dive in today as we talk about linear regression and how it helps us predict continuous outcomes. Understanding the hypothesis in linear regression is important, and hypothesis is essentially an equation that predicts the output, which is y based on certain input which is x. So here the equation help us make predictions, but the key is y which is a continuous value. We want to predict the value h theta, which is the prediction we are going to make or hypothesis we are going to make, to be as close as possible to the actual value y. So in a typical linear regression equation, we have something like this where the hypothesis is consisting of theta zero, theta one, and x. There are three values which…
Contents
-
-
-
-
-
-
(Locked)
Linear regression basics for telecom analytics2m 42s
-
(Locked)
Using hypothesis testing to predict network performance5m 38s
-
(Locked)
Cost function explained: Measuring telecom model accuracy5m 3s
-
(Locked)
Gradient descent: Fine-tuning network models5m 30s
-
(Locked)
Overfitting vs. underfitting: Optimizing for telecom predictions3m 36s
-
(Locked)
-
-
-
-
-
-