joyhuang9473’s gists

joyhuang9473 / coursera-stanford-machine-learning-class-week3-assignment-learning-parameters-using-fminunc.m

Last active March 4, 2020 01:51

Optimizing using fminunc to find the optimal parameters theta in ex2data1.txt.

	% Octave console output
	Cost at theta found by fminunc: 0.203498
	theta:
	-25.161272
	0.206233
	0.201470

joyhuang9473 / coursera-stanford-machine-learning-class-week3-assignment-predict-and-accuracies.m

Last active November 16, 2015 12:46

use the logistic regression model to predict the probability that a student with score 45 on exam 1 and score 85 on exam 2 will be admitted. (in ex2data2.txt)

	% Octave console output
	For a student with scores 45 and 85, we predict an admission probability of 0.776289

	Train Accuracy: 89.000000

joyhuang9473 / coursera-stanford-machine-learning-class-week3-assignment-add-polynomial-features-and-compute-cost.m

Last active November 16, 2015 12:46

Add Polynomial Features And Compute Cost. (mapFeatured X: [X1 X2 (X1.^2) (X2.^2) (X1X2) (X1X2.^2) …])(in ex2data2.txt)

	% Octave console output
	Cost at initial theta (zeros): 0.693147

joyhuang9473 / coursera-stanford-machine-learning-class-week3-assignment-plot-decisionBoundary-with-lambda-0.m

Last active November 16, 2015 12:49

Plot Decision Boundary with lambda 0 (in ex2data2.txt)

	% Octave console output
	Train Accuracy: 86.440678

joyhuang9473 / coursera-stanford-machine-learning-class-week3-assignment-plot-decisionBoundary-with-lambda-1.m

Created November 16, 2015 12:50

Plot Decision Boundary with lambda 1 (in ex2data2.txt)

	% Octave console output
	Train Accuracy: 83.050847

joyhuang9473 / coursera-stanford-machine-learning-class-week3-assignment-plot-decisionBoundary-with-lambda-100.m

Created November 16, 2015 12:51

Plot Decision Boundary with lambda 100 (in ex2data2.txt)

	% Octave console output
	Train Accuracy: 61.016949

joyhuang9473 / coursera-stanford-machine-learning-class-week4-training-one-vs-all-logistic-regression.m

Created November 16, 2015 13:32

K = 10 (0 to 9)(in ex3data1.mat)

	% Octave console output
	Training One-vs-All Logistic Regression...
	Iteration 50 \| Cost: 1.375603e-02 % k = 1
	Iteration 50 \| Cost: 5.725232e-02 % k = 2
	Iteration 50 \| Cost: 6.419917e-02 % k = 3
	Iteration 50 \| Cost: 3.576346e-02 % k = 4
	Iteration 50 \| Cost: 6.183236e-02 % k = 5
	Iteration 50 \| Cost: 2.121825e-02 % k = 6
	Iteration 50 \| Cost: 3.489292e-02 % k = 7
	Iteration 50 \| Cost: 8.559999e-02 % k = 8

joyhuang9473 / coursera-stanford-machine-learning-class-week4-predict-for-one-vs-all.m

Created November 16, 2015 13:37

Predict for One-Vs-All

	% Octave console output
	Training Set Accuracy: 95.020000

joyhuang9473 / coursera-stanford-machine-learning-class-week4-feedforward-propagation-and-prediction.m

Created November 16, 2015 14:13

Feedforward Propagation and Prediction (Loading Saved Neural Network Parameters in ex3weights.mat)

	% Octave console output
	Training Set Accuracy: 97.520000

joyhuang9473 / coursera-stanford-machine-learning-class-week5-feedforward-using-neural-network-and-compute-cost.m

Last active November 16, 2015 15:42

Feedforward Using Neural Network and Compute Cost at parameters (loaded from ex4weights)

	% Octave console output
	Feedforward Using Neural Network ...
	Cost at parameters (loaded from ex4weights): 0.287629
	(this value should be about 0.287629)

	% Octave console output
	Training One-vs-All Logistic Regression...
	Iteration 50 \| Cost: 1.375603e-02 % k = 1
	Iteration 50 \| Cost: 5.725232e-02 % k = 2
	Iteration 50 \| Cost: 6.419917e-02 % k = 3
	Iteration 50 \| Cost: 3.576346e-02 % k = 4
	Iteration 50 \| Cost: 6.183236e-02 % k = 5
	Iteration 50 \| Cost: 2.121825e-02 % k = 6
	Iteration 50 \| Cost: 3.489292e-02 % k = 7
	Iteration 50 \| Cost: 8.559999e-02 % k = 8

Yu-Kai Huang joyhuang9473