BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:138@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20250804T160000
DTEND;TZID=Asia/Kolkata:20250804T170000
DTSTAMP:20250731T044327Z
URL:https://cds.iisc.ac.in/events/cds-kiac-seminar-cds-102-04th-august-exp
 loring-materials-physics-with-shallow-reinforcement-and-generative-machine
 -learning-models/
SUMMARY:CDS-KIAC {Seminar}@ CDS: #102: 04th August: "Exploring Materials Ph
 ysics with Shallow\, Reinforcement and Generative Machine Learning Models"
DESCRIPTION:We welcome you to CDS-KIAC talk on 04th August 2025 (Monday).\n
 The details are as below:\n\n\n\nSpeaker: Prof. Sanghamitra Neogi\, Associ
 ate Professor\, USA\nTitle: "Exploring Materials Physics with Shallow\, Re
 inforcement and Generative Machine Learning Models"\nDate and Time: August
  04\, 2025: 4:00 PM\n\n\n\nAbstract: Machine learning has become a powerfu
 l tool for accelerating materials discovery and uncovering complex structu
 re–property relationships. In this talk\, I will present an overview of 
 how my research leverages shallow models\, reinforcement learning\, and ge
 nerative models to address key challenges in materials physics. My researc
 h group at the University of Colorado Boulder designs analytical and compu
 tational frameworks to investigate phononic\, thermal\, electronic\, therm
 oelectric\, and quantum properties across a broad spectrum of materials. G
 uided by an atom-to-device research philosophy\, we connect atomic-scale p
 hysics to the emergent behavior of complex nanostructures and devices and 
 establish direct links between simulations and experiments. We employ firs
 t-principles electronic-structure methods\, atomistic molecular-dynamics s
 imulations\, and finite-element analysis\, and we increasingly rely on mac
 hine learning models to study material systems that remain inaccessible to
  conventional computational approaches due to their high cost and inherent
  limitations. I will showcase examples from my research\, including predic
 tions of electronic properties of layered semiconductor materials\, mappin
 g composition–property spaces of complex multi-element alloys\, and eluc
 idating how microstructural features influence thermal properties. I will 
 discuss how shallow models provide key physics insights into structure–p
 roperty relationships in cases with limited training data. Using reinforce
 ment learning\, we map the interdependent space of material compositions\,
  atomic arrangements\, and resulting properties and develop approaches tha
 t enable efficient exploration and targeted materials discovery. Generativ
 e models allow us to build multiphysics models and perform inverse design 
 of microstructures with targeted thermal properties. By integrating physic
 al constraints with machine learning\, we aim to enhance model fidelity\, 
 interpretability\, and generalization\, ultimately accelerating the design
  of materials for electronics\, energy\, extreme-environment\, and quantum
  technologies.\n\nBio of Speaker: Sanghamitra Neogi is an Associate Profe
 ssor at the Ann and H.J. Smead Department of Aerospace Engineering Science
 s at the University of Colorado Boulder. Additionally\, she is a Program F
 aculty at the Materials Science and Engineering Program at the University 
 of Colorado Boulder. Prior to joining CU\, she received her B.Sc. and M.Sc
 . in Physics from Jadavpur University\, Kolkata\, and Indian Institute of 
 Technology\, Kanpur\, India\, respectively. She received her Ph.D. in theo
 retical condensed matter physics from the Pennsylvania State University an
 d was a postdoctoral research associate at the Max Planck Institute for Po
 lymer Research\, Mainz\, Germany. Her group\, the CUANTAM (CU Aerospace Na
 noscale Transport Modelling) Lab in the Aerospace Engineering Department\,
  develops computational modeling approaches to investigate the physics of 
 materials in engineering devices functioning in extreme environments. Her 
 research was featured in the IEEE Spectrum feature\, “Physicists Teach A
 I to Simulate Atomic Clusters: Physics-informed machine learning might hel
 p verify microchips\,” (Jul 2021) and received mention in the Journal of
  Physics D: Applied Physics article “The 2022 applied physics by pioneer
 ing women: a roadmap.” She was an Associate Editor for the European Phys
 ical Journal B: Condensed Matter and Complex Systems. She is a 2025 recipi
 ent of the VAIBHAV (Vaishvik Bharatiya Vaigyanik) Fellowship\, awarded by 
 the Department of Science &amp\; Technology\, Government of India.\n\nHost
  Faculty: Prof. Venkatesh Babu\n\n\n\nALL ARE WELCOME
CATEGORIES:Events,Talks
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20240804T160000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR