Results for ""
Location | India |
---|
IISc aims to be among the world’s foremost academic institutions through the pursuit of excellence in research and promotion of innovation by offering world-class education to train future leaders in science and technology and by applying science and technology breakthroughs for India’s wealth creation and social welfare.
IISc is launching a two-year M.Tech. program in Artificial Intelligence, to fill the critical needs of the industry and fill the gap in high-end AI scientists and engineers. This program will be offered by the Division of EECS through the joint efforts of the Departments of CSA, ECE, EE, and ESE.
College Website : https://iisc.ac.in/
Machine Learning Special Interest Group
Machine Learning Special Interest Group Research at IISc is housed in Department of Computer Science and Automation which provides publications in machine learning and related fields. MLSIG conducts research on a variety of aspects of machine learning and related fields, ranging from theoretical foundations to new algorithms as well as several applications. The following are some examples of recent research topics explored in the group:
Machine Learning and Learning Theory Group
Machine Learning and Learning Theory Group current research directions include designing and analyzing algorithms for problems such as ranking and various types of structured prediction tasks, understanding statistical consistency properties for such problems, exploring new issues in machine learning such as those related to privacy, and selected applications of machine learning in computational biology and medicine
Machine and Language Learning lab (MALL)
Machine and Language learning lab primary research goals is to extract, orgazine, and make readily available the knowledge trapped inside such unstructured text data on a large scale. It’s research spans the areas of Machine Learning and Natural Language Processing.
Task agnostic Universal Adversarial Perturbations
Machine learning models are susceptible to adversarial perturbations: small changes to input that can cause large changes in output. It is also demonstrated that there exist input-agnostic perturbations, called universal adversarial perturbations, which can change the inference of target model on most of the data samples.
Existing methods to craft universal perturbations are -
Cross-Modal Retrieval
Increase in the number of sources of data, research in cross-modal matching is becoming an increasingly important area. Several applications like match- ing text with image, matching near infra-red images with visible images example: For matching face images captured during night-time or low-light conditions to standard visible light images in the database), matching sketch images with pictures for forensic applications.
Using Statistical Mechanics to understand depth in Deep Networks
Understanding the representational power of Restricted Boltzmann Machines (RBMs) with multiple layers is an ill-understood problem and is an area of active research. Motivated from the approach of Inherent Structure formalism (Stillinger & Weber, 1982), extensively used in analyzing Spin Glasses, a novel measure has been proposed called Inherent Structure Capacity (ISC), which characterizes the representation capacity of a fixed architecture RBM by the expected number of modes of distributions emanating from the RBM with parameters drawn from a prior distribution.
Fairness in an Algorithmic World
Computation outcomes in economic systems, which are efficient and fair at the same time. This initiative is headed by Siddharth Barman.
Neural programming and program analysis
Automatically synthesizing programs and analyzing their behavior is considered a holy grail of Artificial Intelligence: Neural network-based solutions have been developed towards automating tasks. Deep Neural Networks were employed to identify different vehicles in videos obtained from traffic junctions
This initiative is co-headed by Aditya Kanade and Shirish Shevade.
AI/ML for Next Generation Communication Systems
Investigating the use of AI/ML techniques for communications related applications: Techniques to solve hard problems by training a neural network. Key Investigations under progress - Limited training size & Model generalizability
This initiative is headed by Dr. Chandra R. Murthy.
ARTPARK
Established by the Indian Institute of Science (IISc), ARTPARK is a not for profit in Bengaluru. It is also supported by AI Foundry in a public-private model. With seed funding of $22mn from the Department of Science under the National Mission on Inter-disciplinary Cyber-Physical Systems (NM-ICPS), ARTPARK will bring about collaborative consortium of partners from industry, academia and government bodies. This will lead to cutting-edge innovations in terms of new technologies, standards, products, services and intellectual properties, said the DST
Digital Shadowing
Develop an AI-based framework that could aid in the real-time environment-aware high-fidelity simulation of a windfarm using Deep Learning, Model Order Reduction, High-performance computing.
Using neural networks to solve the equations
One of the major functions of the neural network model is that it can reduce the cost function and eliminate the loss, and we will be able to get the solution. As the initial process changes, we face many challenges when we train the model. We will encounter many scientific challenges when we use machine learning for scientific applications. The primary objective of using machine learning in scientific computing is to eliminate the high computational cost. Therefore, they focus only on transferring the crucial information to build the model. This process is called federated learning. IISc intends to develop an AI-based framework that can help in the real-time environment-aware high-fidelity simulation of a wind farm using Deep Learning, Model Order Reduction, and High-performance computing. However, one of the challenges faced during the process is that these models need to be retrained for changes in simulation parameters which will result in downtime of the framework. Hence there is a need to generate a robust “Digital Shadow” framework which could reliably perform simulation on real-time data with good accuracy and considerable downtime.
Stabilization parameter Prediction
Problem statement
Particle Deposition Prediction
Particle Deposition prediction in the human air pathway using ML.
ANNs for higher order hyperbolic problems
The use of supervised ANNs to improve multi-dimensional extension of current state-of-the-art discontinuous Galerkin solvers which are being used in industry and academic community.With ANNs as black box for inner-element shock capturing, we can improve the robustness and accuracy of current DG methods.