BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//SRMAP Events - ECPv6.15.11//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:SRMAP Events
X-ORIGINAL-URL:https://events.srmap.edu.in
X-WR-CALDESC:Events for SRMAP Events
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:20210101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20220916T160000
DTEND;TZID=Asia/Kolkata:20220916T180000
DTSTAMP:20260422T053536
CREATED:20220914T044600Z
LAST-MODIFIED:20250806T124457Z
UID:141780-1663344000-1663351200@events.srmap.edu.in
SUMMARY:An introduction to federated learning
DESCRIPTION:The Department of Electronics and Communication Engineering is hosting a seminar on September 16\, 2022\, at 4.00 pm as part of the Guest Lecture Series. Dr Anurag Singh\, Associate Professor and Dean of Research and Consultancy\, NIT Delhi\, will deliver a talk on the topic “Federated Learning”. \nAbstract of the talk \nThe most crucial resource for any business\, individual\, or person in the world is data. Everyone\, whether an individual or an institution\, wants to prevent a data breach. High-quality data must be subjected to machine learning algorithms. The model is trained using traditional machine learning techniques\, which save data to one server. There is a chance that this method will expose personal information. A machine learning technique called federated learning (FL) enables machine learning models to train on various datasets located on various sites without sharing data. Without putting training data in a centralised location\, it enables the development of a common global model. Additionally\, it permits personal information to stay in local places\, lowering the risk. \nA new area of machine learning called federated learning already offers greater advantages than conventional machine learning techniques. \nData Security: Training data is kept locally on the devices\, negating the need for a data pool. \nData variety: Heterogeneous data since it incorporates information from various users. \nReal-time continuous learning: Client data is used to enhance models continuously. \nFederated Learning is applied in the field of IoT\, Healthcare\, smartphones\, Advertising\, Autonomous Vehicles etc. \nSpeaker’s Profile \nDr Anurag Singh is currently working as the Associate Professor and Dean of Research and Consultancy at NIT Delhi. He received his PhD from the Indian Institute of Technology Kanpur. His research areas are Network Theory\, Dynamics on/of Networks\, Opinion Dynamics\, Epidemic Modeling\, Intelligent transportation system etc. Dr Anurag Singh has teaching experience at both undergraduate and graduate levels. He has taught courses ranging from the introductory level to specialized courses in Computer Science and Engineering\, and Mathematics. Currently\, he is mentoring students at graduate and undergraduate levels at the National Institute of Technology Delhi\, India. In addition\, he has also been supervising PhD students. He has around 70 publications featured across various leading journals and three DST-funded projects to his credit.
URL:https://events.srmap.edu.in/event/an-introduction-to-federated-learning/
CATEGORIES:Departmental Events,ECE,Events
END:VEVENT
END:VCALENDAR