BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Introduction to Pytorch for image analysis
DTSTART:20260128T110000
DTEND:20260128T130000
DTSTAMP:20260407T224445Z
UID:a2d0c17d4f094cb7ec1b36715d2eddec9288fe70b3947ca57d497233
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Florian Aymanns\nRegistration\n\nJoin us for a hands-on I
 ntroductory PyTorch Workshop\, led by our in-house expert Florian Aymanns\
 , designed for EPFL PhD students and postdocs interested in applying neura
 l networks to image analysis. (Registration required.)\n\nThis session is 
 best suited for participants with basic knowledge of Python who want to 
 learn the foundations of neural networks and their implementation in PyTor
 ch.\n\nWe’ll start by introducing tensors\, highlighting their differen
 ces from NumPy arrays\, and demonstrating autograd with simple examples.
  Moving forward\, we’ll cover key neural network components like convolu
 tional and fully connected layers\, and use them to construct a neural net
 work from scratch.\n\nParticipants will gain an understanding of loss fun
 ctions\, autograd\, and stochastic gradient descent\, learning how weigh
 ts are updated during training. Finally\, we’ll apply these concepts to 
 train an image classification network using PyTorch.\n\nThis workshop offe
 rs a code-along experience on EPFL’s RCP cluster and is perfect for thos
 e eager to begin their journey into machine learning for image analysis.\n
 \nLearning Objectives\n\n	Understand the components of a convolutional neu
 ral network in code\n	Train your first neural network to classify images u
 sing Pytorch\n\n\nPrerequisites\n\n\n	Basic python knowledge\n	Familiarity
  with NumPy arrays\n	Basic understanding of neural networks\n	Understandin
 g of object oriented programming (classes and inheritance) is a plus but n
 ot required\n\n\nLevel\nIntermediate\n\nAbout the Imaging Lunches: \nOnce
  per month\, the EPFL Center for Imaging organises an event dedicated to a
 ll PhD students and postdocs working with/in imaging. Discuss the latest a
 dvances in imaging. Connect with imaging peers. Learn about popular imagin
 g tools!
LOCATION:CE 1 711.2 https://plan.epfl.ch/?room==CE%201%20711.2
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR