BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Neerby//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:neerby-event-21614@neerby.io
DTSTAMP:20260417T112729Z
DTSTART:20260504T173000
DTEND:20260504T193000
SUMMARY:Embracing Noise: How Data Corruption Can Make Models Smarter
DESCRIPTION:PyData St. Louis\nJoin us at PyData St. Louis for a talk and community discussion on how noise and imperfect data can actually make machine learning models stronger.\nMachine learning is often built on the assumption of clean\, high-quality data. In reality\, data is messy\, incomplete\, and noisy. This session explores a powerful idea: introducing controlled corruption during training can improve robustness\, reduce overfitting\, and help models perform better in real-world conditions.\nPizza and networking will begin at 5:30 PM\, and the talk will start at 6:15 PM.\nIn this session\, we’ll cover:\n• Why real-world data is inherently noisy and imperfect\n• How data corruption can act as a form of regularization\n• Different techniques such as Gaussian noise\, masking\, and label flipping\n• How corrupted data improves generalization and resilience to distribution shifts\n• Practical examples in Python from computer vision and NLP\nThe talk is beginner friendly and open to anyone interested in data science\, machine learning\, or applied AI.\nAfter the talk\, we’ll leave time for questions\, discussion\, and networking from 6:50 PM to 7:30 PM with others in the local data community.\nPizza will be provided.\nWho should attend?\nAnyone curious about data science\, machine learning\, or building more robust AI systems\, including students\, professionals\, hobbyists\, and beginners.\nSpecial thanks to Spark Coworking for providing the venue and supporting the local data science community.\nCome learn\, connect\, and be part of the PyData St. Louis community!\nPyData St. Louis is part of the global PyData community. PyData is an educational program of NumFOCUS\, a nonprofit organization that promotes open practices in research\, data\, and scientific computing.
LOCATION:PyData St. Louis\, Saint Louis\, MO
URL:https://neerby.io/event/21614
END:VEVENT
END:VCALENDAR