MachineLearning스터디/LinearRegressionWithMultipleVariables - Revision history

imported>trailblaze at 03:40, 18 February 2014

2014-02-18T03:40:44Z

← Older revision		Revision as of 03:40, 18 February 2014
Line 1:		Line 1:
	~~포맷없는 텍스트를 넣으세요~~
	__TOC__		__TOC__
	* 모든 것을 정리하려고 하니 효율이 떨어진다. 중요하다 생각되는 것만 우선 정리하기로..		* 모든 것을 정리하려고 하니 효율이 떨어진다. 중요하다 생각되는 것만 우선 정리하기로..

2014-02-18T03:39:49Z

← Older revision		Revision as of 03:39, 18 February 2014
Line 1:		Line 1:
			포맷없는 텍스트를 넣으세요
	__TOC__		__TOC__
			* 모든 것을 정리하려고 하니 효율이 떨어진다. 중요하다 생각되는 것만 우선 정리하기로..
			* 이 문서에 있는 사진이나 예제의 상당수는 [https://www.coursera.org/course/ml Coursera/ML강의]에 남겨져 있음. PPT도 제공하므로 꼭 확인하세요.
	=== Multiple Features ===		=== Multiple Features ===
	=== Gradient Descent for Multiple Variables ===		=== Gradient Descent for Multiple Variables ===
Line 92:		Line 94:
	J_history(iter) = computeCostMulti(X, y, theta);		J_history(iter) = computeCostMulti(X, y, theta);
	end		end
			----
			[[MachineLearning스터디]]

2014-02-18T03:38:18Z

← Older revision		Revision as of 03:38, 18 February 2014
Line 11:		Line 11:
	=== Normal Equation ===		=== Normal Equation ===
	[[File:Normal_Equation.PNG]]		[[File:Normal_Equation.PNG]]
			=== 정리 ===
			==== Gradient Descent ====
			* Learning Rate α를 잘 정하는게 중요.
			* Feature의 수가 클 때 사용. (100000개 이상)
			==== Normal Equation ====
			* [[File:invert.png]] 의 계산이 필요. O(N^3)의 시간복잡도를 가짐.
			* Feature의 수가 적을 때 사용. (10000개 까지)
	=== Octave로 Linear Regression With Multiple Varables 구현하기 ===		=== Octave로 Linear Regression With Multiple Varables 구현하기 ===
	==== Feature Normalize ====		==== Feature Normalize ====

2014-02-18T03:30:56Z

← Older revision		Revision as of 03:30, 18 February 2014
Line 3:		Line 3:
	=== Multiple Features ===		=== Multiple Features ===
	=== Gradient Descent for Multiple Variables ===		=== Gradient Descent for Multiple Variables ===
			==== Cost Function ====
			[[File:CostFunctionWithMultipleVariables.PNG]]
	=== Feature Scaling ===		=== Feature Scaling ===
	[[File:Mean_Normalization.png]]		[[File:Mean_Normalization.png]]
Line 8:		Line 10:
	=== Polynomial Regression ===		=== Polynomial Regression ===
	=== Normal Equation ===		=== Normal Equation ===
			[[File:Normal_Equation.PNG]]
	=== Octave로 Linear Regression With Multiple Varables 구현하기 ===		=== Octave로 Linear Regression With Multiple Varables 구현하기 ===
	==== Feature Normalize ====		==== Feature Normalize ====

2014-02-18T03:27:28Z

← Older revision		Revision as of 03:27, 18 February 2014
Line 4:		Line 4:
	=== Gradient Descent for Multiple Variables ===		=== Gradient Descent for Multiple Variables ===
	=== Feature Scaling ===		=== Feature Scaling ===
			[[File:Mean_Normalization.png]]
	=== Learning Rate ===		=== Learning Rate ===
	=== Polynomial Regression ===		=== Polynomial Regression ===

2014-02-18T03:21:26Z

@@ Line 26: / Line 26: @@
   	X_norm(:, i) = (X_norm(:, i ) - mu(i)) / sigma(i);
   end
 * mean : 평균 구하는 함수.
 * std : 표준 편차 구하는 함수.
 * 표준 편차를 이용해서 데이터를 정규화 시킴.

2014-02-18T03:18:15Z

← Older revision		Revision as of 03:18, 18 February 2014
Line 8:		Line 8:
	=== Normal Equation ===		=== Normal Equation ===
	=== Octave로 Linear Regression With Multiple Varables 구현하기 ===		=== Octave로 Linear Regression With Multiple Varables 구현하기 ===
			==== Feature Normalize ====
			function [X_norm, mu, sigma] = featureNormalize(X)
			%FEATURENORMALIZE Normalizes the features in X
			% FEATURENORMALIZE(X) returns a normalized version of X where
			% the mean value of each feature is 0 and the standard deviation
			% is 1. This is often a good preprocessing step to do when
			% working with learning algorithms.

			% You need to set these values correctly
			X_norm = X;
			mu = zeros(1, size(X, 2));
			sigma = zeros(1, size(X, 2));
			n_of_feature = size(X_norm, 2);
			for i = 1:n_of_feature
			mu(i) = mean(X_norm(:, i));
			sigma(i) = std(X_norm(:, i));
			X_norm(:, i) = (X_norm(:, i ) - mu(i)) / sigma(i);
			end

			* mean : 평균 구하는 함수.
			* std : 표준 편차 구하는 함수.
			* 표준 편차를 이용해서 데이터를 정규화 시킴.

2014-02-18T03:15:48Z

← Older revision		Revision as of 03:15, 18 February 2014
Line 1:		Line 1:
	~~Describe MachineLearning스터디/LinearRegressionWithMultipleVariables here~~		__TOC__

			=== Multiple Features ===
			=== Gradient Descent for Multiple Variables ===
			=== Feature Scaling ===
			=== Learning Rate ===
			=== Polynomial Regression ===
			=== Normal Equation ===
			=== Octave로 Linear Regression With Multiple Varables 구현하기 ===

2014-02-10T01:58:24Z

New page

Describe MachineLearning스터디/LinearRegressionWithMultipleVariables here