Tutorial 1: Neural Network to Deep Learning

Abstract: In this tutorial I will discuss  how transition from Neural network to Deep learning had occurred. Further, a brief history of Deep Learning will be presented mainly highlighting the success achieved and criticism that neural network community had under gone over years. We will mainly focus on  various training algorithms used for Deep Learning, tricks that improves the learning. Finally I will Discuss how to implement a simple ANN/CNN and show some important application of  Deep Convolution Networks in computer vision.


Dr. Deepak Mishra is currently an Associate Professor in the Department of Avionics, Indian Institute of Space Science and Technology. His research interests are in Computer vision and Graphics, Image processing, Deep learning and Artificial neural networks, Biometrics, Machine learning, Soft Computing, Computational Neuroscience, Nonlinear Dynamics. He has been awarded the SSI Young Scientist award. He was a postdoctoral Fellow, from 2007-2009 at Health Science Center , University of Louisville Louisville, Kentucky. Dr. Mishra holds a Ph.D. in Electrical Engineering from the Indian Institute of Technology Kanpur, India.


Click here for PPT

Click here for Github files :

Tutorial 2: Machine Learning and AI – From Theory to Practice

AI and machine learning has emerged as the cornerstone of the 4th industrial revolution, transforming almost every aspect of human life. Though the wide scope and rapid research advances in AI might appear intimidating, most learning algorithms rely on few fundamental principles. In this tutorial, we cover some of the most important techniques and principles that are common across popular machine learning and deep learning algorithms, and learn to apply them on few real-world problems. Covered topics shall include basic principles of supervised, unsupervised and reinforcement learning techniques, along with popular machine learning algorithms such as linear regression, logistic regression, Naive Bayes, KNN, K-means,  decision tree and random forest, multi-layer perceptron and deep learning models such as CNN. We shall also touch up on applications of AI in emerging areas such as autonomous marketing and intelligent customer engagement.


This tutorial attempts to be a blend of theory and practice. Participants must bring laptops having at least two cores and 4 GB of RAM, with docker installed. A docker image will be shared for this session.


Jobin Wilson is a Principal Data Scientist – R&D at Flytxt, and leads Flytxt’s AI algorithms R&D group. He is an active researcher and innovator, and is responsible for driving Flytxt’s R&D and intellectual property generation efforts in AI algorithms. He has published several research papers and patents in pattern recognition and machine learning. He holds an MS(Research) in Electrical Engineering from IIT Delhi. He is presently pursuing his Ph.D in Electrical Engineering at the same institution. His research interests include Recommender systems, Artificial Intelligence and online non-stationary learning.