free css templates

About 


The past decade has witnessed dramatic advances in Machine Learning (ML) and Artificial Intelligence (AI). Problems such as image recognition and automated translation between languages are now deemed to have been solved using deep learning techniques. While the training of deep neural networks with many layers and many tunable parameters is reasonably well understood, other ML/AI techniques such as reinforcement learning (programming a machine to learn on the basis of experience) are still in need of a sound analytical foundation. When there is insufficient data to train an AI system (which is generally the case barring a few applications), synthetic data is generated to allow the AI system to compete against itself. Generative Adversarial Networks (GANs) are an example of this approach. However, much foundational research is needed to ensure that the synthetic data generated by GANs is truly representative of the problem at hand.

Reinforcement learning is reminiscent of direct adaptive control which was introduced into control theory during the 1960s. Current approaches to reinforcement learning are based on viewing it as a problem in Markov Decision Processes (MDP) with unknown Markovian dynamics and unknown reward functions. Deep results from statistical learning theory are used to estimate the unknown entities. An analysis of the GAN approach requires showing that various updating rules actually converge to the desired steady state, which is a problem in nonlinear stability theory. Game theory and optimization can also be used to analyze the behavior of two neural networks operating in an adversarial mode. In other words, the techniques and philosophy of control theory, optimization, and game theory have to much to offer to the world of ML and AI, and vice versa.

In view of these observations, it is believed that there is a considerable merit in a workshop that brings together the two disciplines of ML/AI and control theory. The proposed workshop aims to bring together leading experts in these areas who will give an overview of learning, control, game theory, and optimization, and the interplay between these areas.

Objective

While the workshop will be open to all, the primary intended audience consists of junior faculty and research scholars. At the end of the intensive five-day workshop that includes hands-on demos and a panel discussion, those participants who aspire to become researchers should become familiar with the research challenges in the broad areas of learning and control, and the recommended reading list to reach the cutting-edge of research. Those whose aspirations are to become practiced and expert users of ML and control methodologies would be able to realize those goals at the end of the workshop.

Speakers

Pramod P Khargonekar

Vice Chancellor of Research, University of California, Irvine

M Vidyasagar

SERB distinguished Fellow, Indian Institute of Technology Hyderabad

Sanjay P Bhat

Principal Scientist,
Tata Consultancy Services

Puduru Viswanadha Reddy

Indian Institute of Technology, Madras

Schedule

Click here

Registration

Kindly check the details on the following link
http://faculty.iitmandi.ac.in/~tushar/workshop.html

Registration ends in

Sponsors

Contact Details


MANDICON Lab
Indian Institute of Technology Mandi
School of Computing and Electrical Engineering
South Campus
Kamand - 175005, Himachal Pradesh


Tushar Jain
Assistant Professor, IIT Mandi
Coordinator
Ph: +91 1905 267123
email: tushar

Avinash Kumar
PhD scholar, IIT Mandi
Local Arrangement
Mob: +91 8894 181806 
email: d16005

Vyoma Singh
PhD scholar, IIT Mandi
Local Arrangement
Mob: +91 9419 183770
email: vyoma_singh 

Venue

Getting here

Air Travel

The nearest airport to Mandi is the Kullu Airport at Bhuntar, Dharamshala airport at Gaggal and Chandigarh airport. Flights to Kullu are restricted to only from Delhi, and Shimla.

By Road

From Delhi or Chandigarh, one can catch the bus from ISBT (interstate bus terminus). There are different varieties of bus facilities from Delhi and Chandigarh - ordinary, deluxe and AC buses. Alternatively, One can also plan to hire a cab or come by personal vehicle.
HRTC Booking: Check Now
Red Bus Booking: Check Now

Travel Notes

This distance to Mandi can be covered in approximately 12 hrs from Delhi and 6 hrs from Chandigarh (it depends on traffic on the roads or weather conditions) by bus. Transport to IIT Mandi Kamand campus from Mandi town will be arranged by IIT Mandi.


Places to visit nearby