Fundamentals of deep learning using Tensorflow

Abstract: Artificial neural networks form a class of powerful tools capable of approximating highly complex and non-linear functions. They have been quite successful in classifying images, speech recognition or even training a computer to beat a chess Grandmaster.  Over the last few years, neural networks have become popular in other areas of scientific research, such as solving differential equations,  reduced order modelling, uncertainty quantification and turbulence modelling.  Thus, it has become important for researchers in applied sciences to become familiar with the techniques of deep learning.  Keeping this in mind, I will be giving a brief tutorial on the fundamentals of deep learning using Tensorflow.  We will see how neural networks can be used for classification and function regression problems.  The course is intended to give a hands-on experience to the participants to write their own codes to train neural networks.