7. Using the 2 - D data given in file HMMDATA. MAT for a...

7. Using the 2 - D data given in file HMM_DATA. MAT for a Gaussian Mixture Model and the variational Bayes algorithm, estimate the lower bound \mathcal{L} by running the algorithm for different cluster values $k = 2, 3, \dots, 10$ and report the estimated parameters for this optimum cluster value.

Use the concepts discussed in the slides for handwritten dataset. Divide the dataset into train and test set (try 70-30, 80-20 train-test split & see if accuracy varies). Train the following models using the following import statements: (10 points) a. from sklearn.linear_model import LogisticRegression b. from sklearn.tree import DecisionTreeClassifier c. from sklearn.neighbors import KNeighborsClassifier d. from sklearn.discriminant_analysis import LinearDiscriminantAnalysis e. from sklearn.naive_bayes import GaussianNB f. from sklearn.svm import SVC Test the accuracy of each model for the same test data. Generate the heatmap (see below) for the confusion matrix of predictions for each model. (15 points) Find which model has the highest accuracy and what is model accuracy achieved. (5) Try 10 fold cross validation for the models & create a boxplot that shows the accuracy for each model. (20)

Dominador T.

Question

7. Using the 2 - D data given in file HMM_DATA. MAT for a Gaussian Mixture Model and the variational Bayes algorithm, estimate the lower bound \mathcal{L} by running the algorithm for different cluster values $k = 2, 3, \dots, 10$ and report the estimated parameters for this optimum cluster value.

Please give Ace some feedback