Regularization in Deep Learning [Slides]
Govinda Anantha Padmanabha
Regularization is any modification we make to a learning algorithm that is intended to reduce its test error but not training error. This seminar reviews on regularization strategies for deep models or models that may be used as building blocks to form deep models.
Goodfellow Ian, Yoshua Bengio, and Aaron Courville. Deep learning. MIT press, 2016
A review of Markov and hidden Markov Model [Slides]
Both Markov and Hidden Markov models have found wide application in the machine learning and informatics. In this presentation, we review the fundamentals of the two models and discuss about their advantages and disadvantages.
K. Murphy, Machine Learning - A Probabilistic Perspective, Chapter 17, The MIT Press, 2013.