BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260407T175105Z
UID:2884fb56-f8bb-4e87-9585-502fbda0d93d
DTSTART:20261203T090000Z
DTEND:20261204T170000Z
DESCRIPTION:# Overview\nThis course aims to give the participants some prac
 tical knowledge of deep learning models in life sciences.\n \nWith the ris
 e of new technologies\, the volume of omics data in biology and medicine h
 as grown exponentially recently. A major issue is to mine useful predictiv
 e knowledge from these data. Machine learning (ML) is a discipline in whic
 h computer algorithms perform automated learning by using data to assist h
 umans in dealing with a large volume of multidimensional data\, and deep l
 earning is one of these methods. Deep learning is based on artificial neur
 al networks inspired by the structure and function of the human brain. It 
 has been widely applied in computer vision\, natural language processing\,
  computational biology\, etc.\n \nThis course will not make the participan
 t an absolute expert in the complex and dynamic world of Deep-Learning. St
 ill\, it will aim to “break the ice” through the explanation and imple
 mentation of simple yet concrete\, deep-learning models using the PyTorch 
 library. Participants will be introduced to the basic building blocks of d
 eep-learning models and how the main parameters are tuned and monitored to
  ensure the training of large models.\n\n\n# Audience\nThis course is aime
 d at PhD students\, post-docs and researchers in life sciences who already
  know about Machine Learning and would like to discover and start practisi
 ng Deep Learning with PyTorch.\n\n\n# Learning outcomes\nAt the end of the
  course\, the participants will be able to:\n* Create simple deep-learning
  models\n* Identify deep learning parameters\n* Train\, and evaluate a dee
 p-learning auto-encoder model \n* Adapt a pre-existing deep-learning model
  to a new task using fine-tuning\n\n\n# Prerequisites\n##### Knowledge / c
 ompetencies required\n\n* Prior knowledge of ML concepts and methods is re
 quired.\n* A good fluency with the Python programming language\, including
  working knowledge of common data analysis libraries such as numpy\, panda
 \, matplotlib or scikit-learn.\n* Familiarity with different omics data te
 chnologies (highly recommended).\n\n##### Technical\nThe needed libraries 
 are indicated in the [dedicated page on the GitHub repo](\nhttps://github.
 com/sib-swiss/pytorch-practical-training).\n\n\n\n# Application\n\n\nThe r
 egistration fees for academics are **200 CHF** and **1000 CHF** for for-pr
 ofit companies.\n\nWhile participants are registered on a first come\, fir
 st served basis\, exceptions may be made to ensure diversity and equity\, 
 which may increase the time before your registration is confirmed.\n\nAppl
 ications will close on **11/11/2026** or as soon as the places will be fil
 led up. Deadline for free-of-charge cancellation is set to **11/11/2026**.
  Cancellation after this date will not be reimbursed.\n\nYou will be infor
 med by email of your registration confirmation. Upon reception of the conf
 irmation email\, participants will be asked to confirm attendance by payin
 g the fees within 5 days.\n\n# Venue and Time\nThis course will be streame
 d. \n\nThe course will start at 9:00 CET and end around 17:00 CET.\n\nPrec
 ise information will be provided to the participants in due time.\n\n\n#  
 Additional information\nCoordination: Diana Marek\, SIB Training Group.\n\
 nWe will recommend 0.5 ECTS credits for this course (given a passed exam a
 t the end of the course).\n\nYou are welcome to register to the SIB course
 s mailing list to be informed of all future courses and workshops\, as wel
 l as all important deadlines using the form [here](https://lists.sib.swiss
 /postorius/lists/courses.lists.sib.swiss/).\n\nPlease note that participat
 ion in SIB courses is subject to our [general conditions](https://www.sib.
 swiss/training/terms-and-conditions).\n\nSIB abides by the [ELIXIR Code of
  Conduct](https://elixir-europe.org/events/code-of-conduct). Participants 
 of SIB courses are also required to abide by the same code.\n\nFor more in
 formation\, please contact [training@sib.swiss](mailto://training@sib.swis
 s).
SUMMARY:Diving into Deep Learning - Theory and Applications with PyTorch
URL;VALUE=URI:https://www.sib.swiss/training/course/20261203_DEEPP
END:VEVENT
END:VCALENDAR