随笔分类 - Machine Learning
摘要：We can compress our cost function's two conditional cases into one case: We can fully write out our entire cost function as follows: A vectorized impl
阅读全文
摘要：We cannot use the same cost function that we use for linear regression because the Logistic Function will cause the output to be wavy, causing many lo
阅读全文
摘要：x2: midterm exam ^ 2, apply mean normalization: mean value = (7921 + 5184 + 8836 +4761) / 4 = 6675.5 range = 8836-4761 = 4075 ans = (4761 - 6675./5) /
阅读全文
摘要：
阅读全文
摘要：We have used gradient descent where in order to minimize the cost function J(theta), we would take this iterative algorithm that takes many steps, mul
阅读全文
摘要：Quadratic function: Cubic function:
阅读全文
摘要：Feature scaling: it make gradient descent run much faster and converge in a lot fewer other iterations. Bad cases: Good cases: We can speed up gradien
阅读全文
摘要：The gradient descent equation itself is generally the same form; we just have to repeat it for our 'n' features: In other words: The following image c
阅读全文
摘要：Linear regression with multiple variables is also known as "multivariate linear regression". We now introduce notation for equations where we can have
阅读全文
摘要：To compute this formula, you need to do: Actually, to make it simpler, we can do Vectorization, that formula is actually equals to: So we can code it
阅读全文
摘要：For: v = zeros(10, 1); for i=1:10, v(i) = 2^i; end; # the same as indices=1:10 for i=indices, disp(i) end; while & if & break: i=1; while i <=5, v(i)
阅读全文
摘要：t=[0:0.01:0.98]; y1 = sin(2*pi*4*t); plot(t, y1) If you draw tha cos function, it will replace the sin function figure to a new one y2 = cos(2*pi*4*t)
阅读全文
摘要：Mutiplate materix: Everytime you see '.' mean element wise operator. >> A = [1 2; 3 4; 5 6]; >> B = [11 12; 13 14; 15 16]; >> C = [1 1; 2 2]; >> A*C a
阅读全文
摘要：Load data: load featuresX.dat who: Check how many variables in your current session: who whos: details about variables: whos Clear one variable: clear
阅读全文
摘要：You can do baisc math: 5+6 32-8 1/2 2^3 1 == 2 % ans = 0 means false 1 ~=1 % 1 not equals to 2. ans = 1 means true 1 && 0 1 || 0 xor(1, 0) Change the
阅读全文
摘要：We can measure the accuracy of our hypothesis function by using a cost function. This takes an average difference (actually a fancier version of an av
阅读全文
摘要：Evaluation Metrics are how you can tell if your machine learning algorithm is getting better and how well you are doing overall. Accuracy x x x Accura
阅读全文
摘要：The k-means algorithm captures the insight that each point in a cluster should be near to the center of that cluster. It works like this: first we cho
阅读全文
摘要：Decision trees can handle none linear speratable dataset, in the picture, there is none separable dataset When we use dscision tree, we ask multi line
阅读全文
摘要：A support vector machine (SVM) is a supervised machine learning model that uses classification algorithms for two-group classification problems. After
阅读全文
