This tutorial contains brief overview of statistical and machine learning methods for time series forecasting, experiments and comparative analysis of Long short-term memory (LSTM) based architectures for solving above mentioned problem. Single layer, two layer and bidirectional single layer LSTM cases are considered. Metro Interstate Traffic Volume Data Set from UCI Machine Learning Repository and PyTorch deep learning framework are used for analysis.

Continue reading

In this article, we will consider key concepts of discriminative and generative models, differences between them. In the light of these concepts, we will describe logistic regression, Naive Bayes classifier and differentiable generator nets.

Continue reading