Review of state space models [Slides] Souvik Chakraborty Introduction to simulation models for groundwater flow modeling [Slides] Shaoxing Mo Cluster Expansion and Introduction to Alloy Theoretic Automated Toolkit [Slides] Sina Malakpour Regularization in optimization [Slides] Govinda Anantha Padmanabha
An adaptive experimental design for Global sensitivity analysis (GSA) and uncertainty quantification (UQ): Application to groundwater modeling [Slides] Shaoxing Mo Global sensitivity analysis (GSA) and uncertainty quantification (UQ) in groundwater modeling are challenging because of the significant computational requirements. The computationally efficient surrogate method is an alternative solution for this challenge. This week we will introduce a newly proposed adaptive exp
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 [Slide
Implementation of Neural Nets in PyTorch [Slides] Nick Geneva In this seminar we review and discuss the implementation of two different neural nets. First we discuss using mixture density networks to fit Gaussian distributions to a set of toy data and implementing a custom lost function in PyTorch. Second we review and discuss the implementation of a simple Bayesian neural network for a toy classification problem Reference:
C. Bishop, Pattern Recognition and Machine Learning