From Simulation to Experimental Realization of Quadrupedal Walking in Stoch
Dr. Shishir N. Y. Kolathaya
Robert Bosch Centre for Cyber-Physical Systems
Abstract
Stoch is a custom quadrupedal robot designed and developed in the Robert Bosch Center for Cyber Physical Systems at IISc. In contrast to existing approaches, we have used Reinforcement Learning (RL) to realize walking in Stoch. In the talk, we will describe the methodologies used to address high dimensional statespace, transferability to real hardware, and hardware limitations. We first generated walking gaits in simulation. We then realized walking in Stoch by using a low dimensional representation of these gaits, i.e., kinematic motion primitives. This type of methodology improves the transferability of these gaits to real hardware, lowers the computational overhead on-board, and also avoids multiple training iterations by generating a set of derived behaviors from a single learned gait.
Bio
Shishir is an INSPIRE Faculty fellow in the Robert Bosch Center for Cyber Physical Systems (RBCCPS) in IISc Bangalore. He received his Ph.D. degree in Mechanical Engineering (2016) from the GeorgiaInstitute of Technology. His primary focus as a PhD student was on stability and control of walking robots. Shishir is currently interested in safety-critical control, stability of hybrid systems, and deep reinforcement learning for all kinds of robotic platforms.
Date : 29th Feb, 2020
Time: 10:00am-10:50am
Venue: CSA 117
Secure Multi-Party Computation: Overview and Challenges 
Dr. Nishanth Chandran
Principal Researcher
Microsoft Research
View More
Abstract
Can Alice and Bob find out who among them is richer without revealing their net worth to each other? Cryptography, and specifically the primitive of Secure Multi-Party Computation (MPC) provides a mathematical way to do this seemingly impossible task. In fact, early feasibility results in the 1980s showed that any function can also be computed “securely”. Fast forwarding to today’s world, one can ask: can a patient obtain a diagnosis of his/her disease from a diagnostic centre without sharing his/her sensitive medical report with anyone? MPC has come a long way over the last 35 years and is in a position to enable such new and exciting scenarios. The talk will give an introduction to the rich area of MPC and towards the end highlight some of the current research trends in taking MPC to the real world.
Bio
Nishanth Chandran is a Principal Researcher at Microsoft Research, India. His research interests are in problems related to cryptography, cloud security, confidential computing and secure computation. Nishanth is a recipient of the 2010 Chorafas Award for exceptional achievements in research and his research has received coverage in science journals and in the media at venues such as Nature and MIT Technology Review. He holds 4 US Patents and 2 pending US Patents. Nishanth received his Ph.D. in Computer Science from UCLA, M.S. in Computer Science from UCLA, and B.E. in Computer Science and Engineering from Anna University, Chennai.
Date : 29th Feb, 2020
Time: 11:00am-11:50am
Venue: CSA 117
Recent Advances and Trends in NLP: An Application Perspective
Dr. Tejas I. Dhamecha
Research Staff Member
IBM India Research Lab
View More
Abstract
Natural language processing employs computational techniques for the purpose of learning, understanding, and producing human language content. Early computational approaches to language research focused on automating the analysis of the linguistic structure of language and developing basic technologies such as machine translation, speech recognition, and speech synthesis. Today’s researchers refine and make use of such tools in real-world applications, creating spoken dialogue systems and speech-to-speech translation engines, mining social media for information about health or finance, and identifying sentiment and emotion toward products and services. This talk we focus on recent advancements in NLP and see some exciting aplications of same.
Bio
Dr. Tejas I. Dhamecha is a researcher in Cognitive Education Solutions Group at IBM Research, Bengaluru, India. He did his B.E. (Computer Engineering) from Atmiya Institute of Technology and Science, Rajkot in 2010 and Ph.D from Indraprastha Institute of Information Technology (IIIT) – Delhi under the guidance of Dr. Richa Singh and Dr. Mayank Vatsa. He also worked with Dr. Afzel Noore as a Visiting Scholar at West Virginia University, and Dr. Ajay Kumar as a Research Exchange Student at the Hong Kong Polytechnic University. He was recipient of TCS Research Scholarship during my PhD.2q His current research interests are in the areas of Pattern Recognition, Image Processing, Machine Learning, Biometrics, and Natural Language Processing.
Date: 29th Feb, 2020
Time: 2:00pm-2:50pm
Venue: CSA 117
Machine that can Reason: Towards Artificial General intelligence
Dr. Dinesh Garg
Senior Researcher, AI Reasoning
IBM India Research Lab
View More
Abstract
In this talk, we will motivate and introduce the upcoming field of “machine reasoning” which is believed to be a stepping stone towards artificial General Intelligence (AGI). current computers do extremely well on 1 set of tasks but perform miserably when same algorithms are applied to another set. E.g. a computer proficient in playing Chess is clueless when playing AlphaGo or a Natural Language translator which is accurate while translating English fails when attempting the same on French. Also their ability to use reasoning to infer answers from a set of observations is limited. These computers need 2 attributes to match intelligence of humans, i.e. Machine Reasoning and Transfer Learning. Léon Bottou, an expert defined Machine Reasoning as “algebraically manipulating previously acquired knowledge in order to answer a new question”.The goal is to provide a glimpse of recent advances in the field and challenges involved in pushing the boundaries further.
Bio
Dr Dinesh Garg a Senior Researcher in AI Reasoning group working at IBM Research Lab, Bangalore, India. Recently, He spent two years at the Indian Institute of Technology (IIT) Gandhinagar serving as an Associate Professor in the Department of Computer Science and Engineering (CSE). He received his Ph.D. and M.Sc. (Engg.) degrees in Computer Science from Indian Institute of Science (IISc), Bangalore. He works on research problems in the areas of Machine Learning, Deep Generative Models, Latent Variable Models, Deep Adversarial Nets, Deep Nets for NLP, Convex Optimization, Game Theory, Mechanism Design, and Auction Theory.
Date: 29th Feb, 2020
Time: 1:00pm-1:50pm
Venue: CSA 117