Introduction to Deep Learning: Overview, tools and applications
Workshop Objectives: 
To provide an overview of Machine Learning in general and deep learning in particular. Explain the scope and applicability of deep learning Motivate the attendees with real world use cases Introduce to the attendees open source tools such as TensorFlow, Keras and Python 3.6.
Learning Outcomes:
The attendees will learn how to use deep learning tools to construct prototypes of real world applications in multiple domains.
Foundations of Convolutional Neural Networks MNIST Classification using CNN Solving Multi-Class Image Classification Problems: Case Study Improving CNN performance – more techniques Introduction to TensorFlow and Keras Understand the high-level theory and key language around Deep Learning and Generative Adversarial Networks Architect GANs that create convincing images in the style of human-drawn illustrations
Requirements:
♦ Experience in Python (object-oriented programming)
♦ Shell and Bash commands
♦ Fundamentals of Machine learning or statistics
♦ Fundamentals of Deep learning
♦ College calculus 101
Session 1: Using Deep Learning for Natural Language Processing
Summary: Deep learning has revolutionised the techniques of natural language processing (NLP) and multiple organisations are harnessing this emerging NLP capability to enhance their products and services. The technology barrier is significantly reduced with open source technologies that are easy to configure and use. Several generic open source tools are available in machine learning, including deep learning, which can be customized for natural language processing. This presentation will explain to the participants how to use deep learning and customize NLP based applications for their industry.
Session 2: Applications of Deep Learning: Explained with Use Cases
Summary: In recent times, the explosive growth of data and its harnessing through Artificial Intelligence have impacted most of the B2B and B2C businesses and markets. Naturally there is considerable interest in acquiring knowledge and skills in this field. In this half day tutorial, we introduce the motivations, concepts, models and algorithms which are used in deep learning. We then explain how it is applied in domains of natural language processing and image classification. The illustrative prototype applications are constructed using TensorFlow. Participants will learn how to build and deploy deep learning models using TensorFlow.
Session 3: Applied Deep Learning with TensorFlow
Summary: An introduction to Deep Learning with interactive demos using Google’s TensorFlow library and its high-level API, Keras. Essential theory of Deep Learning is provided, with an intuitive understanding of underlying foundations. Also, hands-on code run-throughs provided in Python-based Jupyter notebooks.
Session 4: Generative Adversarial Networks (GANs): Advanced Topics in Deep Learning
Summary: Generative Adversarial Networks (GANs) are deep neural net architectures comprised of two networks, the generator and the discriminator, pitting one against the other (thus the “adversarial”). Recent applications of GANs have enabled the fabrication of stunning and realistic images with flexible, user-specifiable elements.
Session 5: Introduction to Deep Learning with Applications
Summary: This workshop covers the essentials of deep learning from a mathematical and programming perspective.
♦ What is deep learning?
♦ Types of deep learning
♦ Mathematics of Deep Learning: universal approximation using neural nets, Backpropagation, and techniques for fitting deep learning nets.
♦ Programming deep learning: tensorflow, mxnet, h2o in R and Python with illustrated applications.
Presenters:
Jayadeep Shitole is a Research Analyst and Software Developer at OptiRisk Systems. He provides support to hedge fund clients of OptiRisk Systems in setting up their algorithmic trading systems. He has also been employed as a Data Scientist for a leading Big Data analytics company, where he worked on designing, developing, and deploying data-driven predictive models to solve business problems using machine learning and statistical modelling.
Dr. Nishant Chandra has driven machine learning and natural language innovation in BFSI, e-commerce, R&D, and mobile telecom industries in USA and India. He developed and implemented natural language predictive models that are deployed in top banks and telecom companies resulting in significant impact across their value chain.
For his contributions, Dr. Chandra was acknowledged as one of the top 10 data scientists in India. He has received the prestigious Barrier Fellowship and several other awards and marks of recognition. The Department of Homeland Security, United States Government, has classified Dr. Chandra as an outstanding researcher.
He was the conference session chair for the GSPx conference at San Jose, California. He has been a reviewer for IEEE transactions, served on the editorial board of the Human Language Technology conference, and spoken at several international conferences. He also has five assigned patents and several journal and conference publications. Dr. Chandra is a passionate puzzler who invents puzzles and has represented India in the World Puzzle Championship at Stamford, Connecticut. He received his Ph.D. in Electrical and Computer Engineering from Mississippi State University.
Dr. Chandra is currently Data Science Leader at AIG.
Sanjiv Das is the William and Janice Terry Professor of Finance at Santa Clara University’s Leavey School of Business. He was previously Associate Professor at Harvard Business School and UC Berkeley. He holds post-graduate degrees in Finance (M.Phil and Ph.D. from New York University), Computer Science (M.S. from UC Berkeley), an MBA from the Indian Institute of Management, and is a qualified Cost and Works Accountant.
He edits several academic journals. Prior to being an academic, he worked in the derivatives business as a Vice-President at Citibank. His current research interests include: the modeling of default risk, machine learning, social networks, derivatives pricing models, portfolio theory, and venture capital. He has published over ninety articles in academic journals, and won numerous awards for research and teaching. His recent book “Derivatives: Principles and Practice” was published in May 2010. He currently also serves as a Senior Fellow at the FDIC Center for Financial Research.
