machine learning certification by stanford university coursera

It should be this time last year, I started to get into the knowledge of machine learning, then the introductory book is "Introduction to data mining." Swallowed read the various well-known classifiers: Decision Tree, naive Bayesian, SVM, neural network, random forest and so on; In addition, more serious review of statistics, learning the linear regression, but a

is more than one, the Newton method iterates over the rule:Newton's method usually has a faster convergence rate than the batch gradient, and it takes a much smaller number of iterations to get close to the minimum value. However, when the parameters of the model are many (n), the computational cost of the Hessian matrix will be large, resulting in a slower convergence rate, but when the number of arguments is not long, the Newton method is usually much faster than the gradient descent.Summariz

based on the minimum mean variance. The closer to the predicted point, the heavier the weight, which is to use the points near the check to give higher weights. The most common is the Gaussian nucleus. The weights corresponding to the Gaussian nuclei are as follows:In (Formula 2), the only thing we need to make sure is that it's a user-specified parameter that determines how much weight is given to nearby points.Therefore, as shown in (Equation 3), local weighted linear regression is a non-para

symmetric semi-definite matrixin the case where the data is non-linear:called L1 norm soft margin SVM. is a convex optimization problem. It allows an interval of less than 1, which allows for the categorization of errors. SMO algorithm:coordinate ascent algorithm:This algorithm has more iterations, but at some point the inner loop will be very fast if a parameter in W (A1,,, am) is very small at the cost of finding the optimal value. SMO:If only one α is solved as SVM, the other α is fixed. obt

endfunction Initializes the matrix for the preceding dataset. Call a function to calculate the value of the cost function. 1> X = [1 1; 1 2; 1 3]; 2> Y = [1; 2; 3]; 3> Theta = [0; 1]; % records is 0, 1 h (x) = x. The value of the cost function is 04> J = costfunctionj (X, Y, theta) 5 J = 0. 1> Theta = [0; 0]; % values is 0, 0 h (x) = 0. data cannot be fitted at this time. 2> J = costfunctionj (X, Y, theta) 3 J = 2.33334 5> (1 ^ 2 + 2 ^ 2 + 3 ^ 2)/(2*3) % value of the cost function 6 ans = 2

regression as shown below, (note that in matlab the vector subscript starts at 1, so the theta0 should be theta (1)).MATLAB implementation of the logistic regression the function code is as follows:function[J, Grad] =Costfunctionreg (Theta, X, y, Lambda)%costfunctionreg Compute Cost andgradient for logistic regression with regularization% J=Costfunctionreg (Theta, X, y, Lambda) computes the cost of using% theta as the parameter for regularized logistic re Gression andthe% Gradient of the cost w

1. use of MATLAB and octave2. Nouns to be understood (convexity optimization, implicit Markov chain)3. Some definitions of data mining:A computer application, assuming that there is a task T, then there is a performance measurement method p, under the influence of experience E, p on t measurement results are improved.4. Vector machine concept: used to transform an infinite dimension vector into a finite number of dimensions.5. Classification of

,....} (A is the 1th word in the dictionary and Nip is the No. 35000 Word). So for naive Bayes, it can be expressed as the following matrix (the 1th element of the matrix is 1, and the No. 35000 element is also 1)in the multinomial event model, it is expressed as,. This means that the 1th word of the message is a, and the No. 35000 Word is nip. In this case, if the 3rd word in the message is a, the naive is unchanged, but the representation in the Multinomial event model will be x3=1. This allow

algorithm solves the problem of large optimization by decomposing it into several small optimization problems. These small optimization problems are often easy to solve, and the results of sequential solution are consistent with the results of solving them as a whole.The SMO works based on the coordinate ascent algorithm.1, coordinate ascentAssume that the optimization problem is:We select one of the parameters in turn to optimize this parameter, which causes the W function to grow fastest.The

returnWhen the classification problem is no longer two yuan but K yuan, that is, y∈{1,2,..., k}. We can solve this classification problem by constructing the generalized linear model. The following steps are described.Suppose y obeys exponential family distribution, φi = P (y = i;φ) and known. So. We also define.Also 1{} The condition for the representation in parentheses is the true value of the entire equation is 1, otherwise 0. So (T (y)) i = 1{y = i}. From the knowledge of probability theor

equal to 0.3. Optimal interval classifierThe optimal interval classifier can be defined asSo set its limit toSo its LaGrand day operator isThe derivation of its factors is obtained by:ObtainedIt is possible to differentiate its factor B by:The (9) type (8) can beAnd then by the (10) type of generationSo the dual optimization problem can be expressed as:The problem of dual optimization can be obtained, so that the Jiewei of B can be obtained by (9).For a new data point x, you can make prediction

23:55:01 | category: foreign university courses | Tag: machine learning | font size subscription INSTRUCTOR: Andrew Ng Http://see.stanford.edu/see/courseinfo.aspx? Coll = 348ca38a-3a6d-4052-937d-cb017338d7b1 Http://www.stanford.edu/class/cs229/materials.html Lecture Notes 1 (PS) (PDF) Supervised Learn