2-Day IEEE Workshops on Machine Learning, Convolutional Neural Networks and Tensorflow, 24th & 25th September 2018

Monday, September 24th, 2018 at 4:00 PM to 9:00PM

TI Auditorium

PROGRAM

4:00 - 4:15 PM Registration & Networking
4:15 - 9:00 PM Workshop

NOTE: Same timings for 24th & 25th September

REGISTRATION

Chair: Dr. Kiran Gunnam
Organizer: IEEE ComSoC, ITSoC, CIS and Apollo AI
    

Session Abstract:As data sources proliferate along with the computing power to process them, going straight to the data is one of the most straightforward ways to quickly gain insights and make predictions. Machine learning brings together computer science and statistics to harness that predictive power. Itís a must-have skill for all aspiring data analysts and data scientists, or anyone else who wants to wrestle all that raw data into refined trends and predictions.

This is a training that will teach you the end-to-end process of investigating data through a machine-learning lens. It will teach you how to extract and identify useful features that best represent your data, a few of the most important machine learning algorithms, and how to evaluate the performance of your machine learning algorithms. In this short course, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical knowledge needed to quickly and powerfully apply these techniques to new problems.

This series of workshops are focused on explaining the foundations and intuitions of machine learning along with guided programming exercises. It describes deep learning techniques used by practitioners in industry, including classic machine learning techniques, deep convolutional neural networks, regularization, optimization algorithms, and practical methodology with focus on guided examples in computer vison applications.

Discounts are available for IEEE Members,sponsoring chapter members and Texas Instruments Employees.

If you are attending both the days of the workshop, you can buy the combined ticket instead of buying two separate tickets for each day.

Early bird tickets last till end of July 15th. Regular registration from July 16th to August 15th.

Late registration is from August 16th to September 18th.
Workshop Schedule:

Workshop 1:

4:00 PM-4.15 PM (PT) Check In/Networking/Refreshments,
4:15 PM-9.00 PM Workshop 1

Workshop 2:

4:00 PM- 4.15 PM (PT) Check In/Networking/Refreshments,
4:15 PM-9.00 PM Workshop 2

Location/Venue:

Texas Instruments Silicon Valley Auditorium
(formerly National Semiconductor Auditorium E)
2900 Semiconductor Dr
Santa Clara, CA 95051

Registrations close on September 18th, one week before the workshop.

Speaker: Dr. Kiran Gunnam

Bio: Dr. Gunnam is an innovative technology leader with vision and passion who effectively connects with individuals and groups. Dr. Gunnam's breakthrough contributions are in the areas of advanced error correction systems, storage class memory systems and vision based navigation systems. He has helped drive organizations to become industry leaders through ground-breaking technologies. Dr. Gunnam has 70 issued patents and 100+ patent applications/invention disclosures on algorithms, computing and storage systems. He is the lead inventor/sole inventor for 90% of them. Dr. Gunnamís patented work has been already incorporated in more than 2 billion data storage and WiFi chips and is set to continue to be incorporated in more than 500 million chips per year.

Dr. Gunnam served as IEEE Distinguished Speaker and Plenary Speaker for 19 events and international conferences and more than 2000 attendees in USA, Canada and Asia benefited from his lecture talks. He also teaches graduate level course focused on machine learning systems at Santa Clara University.

Title: Workshop 1: Machine Learning Foundations -An Intuitive Approach

Abstract: This first workshop offers an intuitive treatment of the important machine learning approaches. The workshop covers supervised Learning and unsupervised learning. Various classic machine learning as well as modern deep neural networks and deep belief networks are covered. How to build an end-to-end application is covered in depth focusing on selecting right machine learning algorithm, data preprocessing and evaluating model.

Speaker: Dr. Kiran Gunnam

Title: Workshop 2: Deep learning with CNN and Tensorflow

Abstract: This second workshop offers an in-depth treatment of Convolutional neural networks (CNN) and explain each layer in detail. It also covers various architecture optimization techniques including data optimization, drop outs, layer patterns and sizing. It provides a comprehensive case study of recent CNN architectures including AlexNet, ZFNet and GoogleNet.

Tensorflow basics would be covered. Guided exercises in Tensorflow involve programming linear regression and nearest neighbors approaches, building a simple neural network for XOR, building CNN for handwritten digits recognition. Template software functions are provided with most of the software is written except for the key concepts. Instructor will work with attendees to help them complete the solutions.

Attendees for workshop 2 should bring their own laptop with Tensorflow installed. Installation links:

https://www.tensorflow.org/

For the detailed list of topics covered, please see the list of topics at:

https://drive.google.com/open?id=1N3v5Thf5OX-WqyHuoVp7Eec4FOoOCm-C

Course slides in PDF and other workshop materials will be shared with registered attendees 5-days before the course.

Abstract: Target Audience

Engineers, researchers, practitioners and students who are interested in machine learning, convolutional neural networks, recurrent neural networks, reinforcement learning and their implementations on GPUs and FPGAs. This workshop series will particularly benefit people who intend to develop machine learning techniques and applications that can keep improving themselves after seeing more and diverse data to achieve intelligence.

Key words: Machine Learning, Deep Learning, Supervised Learning, Unsupervised learning, CNN, RNN, GPU, FPGA

Prerequisite Knowledge: Basic knowledge of matrices, vectors, derivatives, probability. You may also want to review these guides useful : https://drive.google.com/open?id=1rQBqsaN709vWMGk4_MDjAc2eiaxFayTx