From 98765d314e52ccadc9e4d2bac1e06fb1aecbbf25 Mon Sep 17 00:00:00 2001
From: brian dalessandro <briand@gmail.com>
Date: Thu, 4 Oct 2018 08:47:27 -0400
Subject: [PATCH] bv

---
 ipython/python35/Lecture_BiasVariance_3.ipynb | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/ipython/python35/Lecture_BiasVariance_3.ipynb b/ipython/python35/Lecture_BiasVariance_3.ipynb
index 39bea57..66f726a 100644
--- a/ipython/python35/Lecture_BiasVariance_3.ipynb
+++ b/ipython/python35/Lecture_BiasVariance_3.ipynb
@@ -14,7 +14,7 @@
     "\n",
     "The word \"model\" alone implies some simplification of the world, and such simplifications generally accept a level of misrepresentation for the sake of parsimony (ie., simplicity). The challenge we face as Data Scientists is that the world we are usually trying to model produces data that is inherently noisy. Modeling such noisy systems requires a delicate balancing act between model parsimony and generalizability. When our measurement systems are rife with uncertainty, the desire to build simpler models isn't just a stylistic choice - it is an essential practice if we desire to successfully generalize on unknown data.<br><br>\n",
     "\n",
-    "The Bias-Variance tradeoff is a theoretical concept that fortunately can be very intuitive and easy to illustrate. This notebook aims to offer the reader both views. On the theory side, we'll define and explain some core constructs and show how the common least squares error can be decomoposed into both bias and variance components. To make the concepts more intuitive, we'll present multiple illustrations with simulated data. The rest of this notebook is organized as follows:<br>\n",
+    "The Bias-Variance tradeoff is a theoretical concept that fortunately can be very intuitive and easy to illustrate. This notebook aims to offer the reader both views. On the theory side, we'll define and explain some core constructs and show how the common least squares error can be decomposed into both bias and variance components. To make the concepts more intuitive, we'll present multiple illustrations with simulated data. The rest of this notebook is organized as follows:<br>\n",
     "\n",
     "\n",
     "<ul>\n",
@@ -25,7 +25,7 @@
     "</p>\n",
     "\n",
     "## Intuitive Explanation of Bias and Variance.\n",
-    "<p>Both \"bias\" and \"variance\" are common terms in statistics, and their general meaning isn't that far from how they are used in statistical learning theory. If you recall in statistics, the bias of an estimator is defined as the difference between the expected value of an estimator and the true value of the quantity being estimated. The \"bias\" and \"variance\" of a predictive model follow the same idea since you can think of a model as a function that estimates the expected value of an outcome $Y$ conditional on some $X=x$,  (i.e., $f(x)=E[Y|X=x]$).\n",
+    "<p>Both \"bias\" and \"variance\" are common terms in statistics, and their general meaning isn't that far from how they are used in statistical learning theory. If you recall in statistics, the bias of an estimator is defined as the difference between the expected value of an estimator and the true value of the quantity being estimated. The \"bias\" and \"variance\" of a predictive model follow the same idea since a \"model\" is really just some function that estimates the expected value of an outcome $Y$ conditional on some $X=x$,  (i.e., $f(x)=E[Y|X=x]$).\n",
     "\n",
     "<br><br>\n",
     "\n",