BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Aerospace Engineering - ECPv6.6.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://aero.iisc.ac.in
X-WR-CALDESC:Events for Department of Aerospace Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20240801T103000
DTEND;TZID=Asia/Kolkata:20240801T113000
DTSTAMP:20260517T114638
CREATED:20240801T054703Z
LAST-MODIFIED:20240803T054737Z
UID:10000011-1722508200-1722511800@aero.iisc.ac.in
SUMMARY:[PhD Colloquium] Development of Generalizable Spiking Neural Network-based Learning Frameworks for Solving Perimeter Defense Problem
DESCRIPTION:Spiking Neural Networks (SNNs) are third-generation neural networks that can process information in a more biologically realistic way compared to other neural networks such as sigmoidal networks. They process the information in terms of spike which is considered as a discrete event in time. Due to their high energy efficiency\, SNNs are used in various applications such as classification\, prediction\, assignment\, recognition\, etc. In this thesis\, the capability of SNNs to solve the SpatioTemporal MultiTask Assignment (STMTA) problem which is formulated from a Perimeter Defense Problem (PDP) is explored. \nDue to the efficiency of SNNs in handling spatiotemporal data\, they are used to develop learning-based frameworks to solve the PDP. Initially\, a time-varying weight SNN for decentralized assignment learning for a critical PDP is presented in this thesis. A Decentralized sequential Assignment Learning with Spiking neural networks (abbreviated as DeALS) approach is proposed for the PDP which can approximate the relation between intruder velocity\, shape of the territory\, size of the defender team\, and protection area. In DeALS\, a multitask assignment SNN is developed for each defender to protect the perimeter. This time-varying weight multitask assignment SNN is trained in a supervised manner to approximate the ground truth obtained from the existing external solution for PDP. To reduce the usage of external ground truth algorithms the greedy assignment learning-based frameworks are developed to solve PDP in a decentralized manner. Due to the decentralized training of SNN\, conflicts are found in the final defender assignments. Therefore to resolve this conflicts an additional conflict-free trajectory generation algorithm is used. Further\, in the thesis to reduce the usage of a conflict-free trajectory generation algorithm an SNN which can generate conflict-free assignments is developed to solve PDP. A centralized greedy assignment learning solution is developed for PDP using the aforementioned conflict-free assignment SNN. These conflict-free assignments are obtained with the help of inhibitory connections among the assignment neurons in the SNN. \nFurther\, the inhibitory connections are used to develop efficient deep SNNs for classification purposes. The inhibitory connections are motivated by biology. These inhibitory connections make sure that the first spiking neurons in a layer acquire knowledge efficiently about the input by inhibiting the response of other neurons in the same layer. A Distributed Coding SNN (DC-SNN) architecture with inhibitory connections in the hidden layer is developed for solving classification problems. With the help of Temporal Separation Modulated Spike Timing Dependent Plasticity (TSM-STDP) learning it is demonstrated that a DC-SNN is suitable for early interruption which helps in faster classification. Eventually\, in this thesis\, SNN classifiers with time-varying weights without hidden layers are developed which are capable of inherent interpretations. The time-varying weights are modeled using random Gaussian mixtures spread across the simulation interval.  By establishing relationships between the amplitudes of time-varying weights and the spike patterns of the neurons in the architecture\, the decisions of these spiking neural classifiers are interpreted. \n  \nSpeaker: P. Mohammed Thousif
URL:https://aero.iisc.ac.in/event/phd-colloquium-development-of-generalizable-spiking-neural-network-based-learning-frameworks-for-solving-perimeter-defense-problem/
LOCATION:STC Seminar Hall\, Dept. of Aerospace Engineering
CATEGORIES:Thesis Colloquium / Defence
ATTACH;FMTTYPE=image/jpeg:https://aero.iisc.ac.in/wp-content/uploads/2024/04/Thesis-Colloquium-Defence.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20240823T160000
DTEND;TZID=Asia/Kolkata:20240823T170000
DTSTAMP:20260517T114638
CREATED:20240822T090144Z
LAST-MODIFIED:20240822T090919Z
UID:10000018-1724428800-1724432400@aero.iisc.ac.in
SUMMARY:Recent Advances in Infrared Optics: From Metalenses to Upconversion  Imaging
DESCRIPTION:Infrared imaging and spectroscopic sensing are strategic technologies with diverse applications in defense\, space\, industrial monitoring\, medical diagnosis and treatment. Advancements in infrared sensing technology over the years has relied on key developments in light sources\, detectors\, optical components and image processing techniques. However\, the high costs of infrared coherent light sources\, poor performance of cooled focal plane-arrays\, and use of exotic materials for building lenses\, filters\, polarizers etc. has been a deterrent in finding widespread use for this technology. There is an ongoing effort worldwide to realize high-performance yet\, practically relevant optical hardware solutions for infrared sensing and imaging. In this talk\, I will give an overview of this field drawing on personal pain points working on the applications. I will also discuss in detail three key developments in this area\, namely: (i) small foot-print metalenses for building lowcost infrared imaging systems\, (ii) high-performance\, resonant metasurfaces as wavelength selective filters for multispectral applications\, and (iii) up-conversion imaging as an alternative for direct infrared detection by converting infrared photons to the visible range for detection using high performance silicon sensors. \nSpeaker: Prof. Varun Raghunathan \nBiography: Varun Raghunathan is an Associate Professor at the ECE department\, Indian Institute of Science\, Bangalore\, India. His research group works broadly in the area of experimental optics with interest in nonlinear optics\, integrated nanophotonics\, biophotonics\, optical and quantum communications. He obtained his Ph.D. degree in electrical engineering from the University of California Los Angeles\, Los Angeles\, CA\, USA\, in 2008\, working on silicon photonics. From 2009 to 2012\, he was a Postdoctoral Scholar with the Department of Chemistry\, University of California Irvine\, Irvine\, CA\, USA\, working in the area of nonlinear optical microscopy. He was also Research Scientist with Agilent Research Laboratories\, Santa Clara\, CA\, USA from 2012 to 2016\, working in the areas of infrared micro-spectroscopy with applications of novel optical sensing techniques in digital pathology.
URL:https://aero.iisc.ac.in/event/recent-advances-in-infrared-optics-from-metalenses-to-upconversion-imaging/
LOCATION:Auditorium (AE 005)\, Department of Aerospace Engineering
CATEGORIES:AE Seminar
ATTACH;FMTTYPE=image/jpeg:https://aero.iisc.ac.in/wp-content/uploads/2024/04/AE-Seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20240826T150000
DTEND;TZID=Asia/Kolkata:20240826T160000
DTSTAMP:20260517T114638
CREATED:20241118T084323Z
LAST-MODIFIED:20241118T084323Z
UID:10000019-1724684400-1724688000@aero.iisc.ac.in
SUMMARY:Guidance for Pursuit and Evasion
DESCRIPTION:Traditional pursuit-evasion engagements are concerned with a single pursuer chasing a single target. Current and future engagements may include more than two adversaries. In my talk I will present some new guidance concepts we developed for: 1-on-1\, N-on-1\, 1-on-N\, and N-on-M engagements. Special emphasis will be given to the underlying geometrical rules for guidance as well as to the presentation and analysis of some interesting cooperative guidance schemes. \nSpeaker: Prof. Tal Shima \nBiography: Tal Shima received his B.Sc.\, MA\, and Ph.D. degrees\, all in Aerospace Engineering\, from the Technion – Israel Institute of Technology. He also received the MBA degree from the Tel-Aviv University. Since 2006 Dr. Shima is with the Department of Aerospace Engineering at the Technion where he currently holds the Lottie and Max Dresher Chair in Aerospace Performance and Propulsion. He recently finished his 4 years’ term as dean of the department. His current research interests are in the area of guidance of autonomous vehicles\, especially aerial ones\, operating individually or as a team. He is the author/co-author of more than 100 archival journal papers in these research areas.
URL:https://aero.iisc.ac.in/event/guidance-for-pursuit-and-evasion/
LOCATION:Auditorium (AE 005)\, Department of Aerospace Engineering
CATEGORIES:AE Seminar
ATTACH;FMTTYPE=image/jpeg:https://aero.iisc.ac.in/wp-content/uploads/2024/04/AE-Seminar.jpg
END:VEVENT
END:VCALENDAR