MAT 555E - Hesaplamalı Bilimler için İstatistiksel Veri Analizi

Dersin Amaçları

This course is designed to provide necessary mathematical and computational background on statistical data analysis tools and algorithms needed by graduate students working in applied sciences.

Dersin Tanımı

The differences between statistics, machine learning and data science. Basic statistics and hypothesis testing. Optimization techniques. Least square regression. Regularization, ridge and lasso regression. Logistic and probit regression. PCA, LDA and SVM. Classification and clustering. K-NN and K-means algorithms. Entropy and gini. Decision trees and random forests. Bayes rule and naive Bayes algorithm. Perceptron. Computation graphs and artificial neural networks. Examples. Hopefield networks.