solves neural networks learning quiz

Author: anishLearnsToCode

README.md

@@ -58,3 +58,8 @@ __Instructor__: Andrew Ng.
     - [One vs. All Multi Class Classifier](week4/machine-learning-ex3/ex3/oneVsAll.m)
     - [Predict one vs. all Multi Class Classifier](week4/machine-learning-ex3/ex3/predictOneVsAll.m)
     - [Neural Network Prediction Function](week4/machine-learning-ex3/ex3/predict.m)
+
+
+## Week 5
+### Quizzes
+- [Neural Networks: Learning](week5/neural-networks-quiz.md)

week4/machine-learning-ex3/ex3/predict.m

@@ -1,43 +1,15 @@
 function p = predict(Theta1, Theta2, X)
-%PREDICT Predict the label of an input given a trained neural network
-%   p = PREDICT(Theta1, Theta2, X) outputs the predicted label of X given the
-%   trained weights of a neural network (Theta1, Theta2)
-
-% Useful values
-m = size(X, 1);
-num_labels = size(Theta2, 1);
-
-% You need to return the following variables correctly 
-% p = zeros(m, 1);
-
-% add x0 in x
-a1 = [ones(m, 1) X];
-a2 = sigmoid(a1 * Theta1');
-a2 = [ones(m, 1) a2];
-a3 = sigmoid(a2 * Theta2');
-[maxProbability index] = max(a3, [], 2);
-p = index;
-
-% ====================== YOUR CODE HERE ======================
-% Instructions: Complete the following code to make predictions using
-%               your learned neural network. You should set p to a 
-%               vector containing labels between 1 to num_labels.
-%
-% Hint: The max function might come in useful. In particular, the max
-%       function can also return the index of the max element, for more
-%       information see 'help max'. If your examples are in rows, then, you
-%       can use max(A, [], 2) to obtain the max for each row.
-%
-
-
-
-
-
-
-
-
-
-% =========================================================================
-
-
+  %PREDICT Predict the label of an input given a trained neural network
+  %   p = PREDICT(Theta1, Theta2, X) outputs the predicted label of X given the
+  %   trained weights of a neural network (Theta1, Theta2)
+
+  % training data size
+  m = size(X, 1);
+
+  a1 = [ones(m, 1) X];
+  a2 = sigmoid(a1 * Theta1');
+  a2 = [ones(m, 1) a2];
+  a3 = sigmoid(a2 * Theta2');
+  [maxProbability index] = max(a3, [], 2);
+  p = index;
 end

week4/machine-learning-ex3/ex3/token.mat

@@ -1,4 +1,4 @@
-# Created by Octave 5.2.0, Mon Jun 15 03:58:24 2020 GMT <unknown@anishLearnsToCode>
+# Created by Octave 5.2.0, Mon Jun 15 04:01:39 2020 GMT <unknown@anishLearnsToCode>
 # name: email
 # type: sq_string
 # elements: 1

week5/assets/quiz-1.PNG

@@ -0,0 +1,7 @@
+# Neural Networks: Learning
+
+![Question 1](assets/quiz-1.PNG)
+![Question 2](assets/quiz-2.PNG)
+![Question 3](assets/quiz-3.PNG)
+![Question 4](assets/quiz-4.PNG)
+![Question 5](assets/quiz-5.PNG)

week5/assets/quiz-2.PNG

@@ -0,0 +1,23 @@
+clc;
+clear;
+
+% Gradiant Approximater (Gradiant Checker)
+function gradent = approximateGradient(theta, cost) 
+  n = length(theta);
+  gradient = zeros(n, 1);
+  EPSILON = 1e-4;
+  for i = 1:n
+    thetaPlus = theta;
+    thetaPlus(i) += EPSILON;
+    thetaMinus = theta;
+    thetaMinus(i) -= EPSILON;
+    gradent(i) = (cost(thetaPlus) - cost(thetaMinus)) / (2 * EPSILON);
+  endfor
+endfunction
+
+function J = costFunction(theta)
+  J = 100 * rand(1, 1);  
+endfunction
+
+hypothesis = [0 ; 1 ; 2];
+disp(approximateGradient(hypothesis, @costFunction));