From d155dbb875ce1b706dc1ada0914db711b6865840 Mon Sep 17 00:00:00 2001 From: Moiz Sajid Date: Wed, 10 May 2017 15:08:15 +0500 Subject: [PATCH] 2016-11-06-tutorial-1.markdown It should be c1 and c0. A possible mistake! --- _posts/2016-11-06-tutorial-1.markdown | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_posts/2016-11-06-tutorial-1.markdown b/_posts/2016-11-06-tutorial-1.markdown index 38fa5b6..ab11150 100644 --- a/_posts/2016-11-06-tutorial-1.markdown +++ b/_posts/2016-11-06-tutorial-1.markdown @@ -158,7 +158,7 @@ $$y=mx+b$$ $$y(x)$$ is our output, or in this case the price of a house, and $$x$$ is our feature, or in this case the size of the house. $$c_{0}$$ is the y intercept, to account for the base price of the house. -Now the question becomes: How does a machine learning algorithm choose $$c_{2}$$ and $$c_{1}$$ so that the line best predicts house prices? +Now the question becomes: How does a machine learning algorithm choose $$c_{1}$$ and $$c_{0}$$ so that the line best predicts house prices? *It’s worth noting here that the coefficients can actually be found directly and very efficiently through a matrix relation called the [normal equation](http://mathworld.wolfram.com/NormalEquation.html). However, since this method becomes impractical when working with hundreds or thousands of variables, we'll be using the method machine learning algorithms often use.