BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260627T145918Z
UID:8bb25c59-739c-4814-8ee7-101d34b91181
DTSTART:20241107T090000Z
DTEND:20241108T170000Z
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 explaination and impl
 ementation of simple yet concrete\, deep-learning models using the PyTorch
  library. Participants will be introduced to the basic building blocks of 
 deep-learning models and how the main parameters are tuned and monitored t
 o ensure the training of large models.\n\n\n# Audience\nThis course is aim
 ed at PhD students\, post-docs and researchers in life sciences who alread
 y know about Machine Learning and would like to discover and start practis
 ing Deep Learning with PyTorch.\n\n\n# Learning outcomes\nAt the end of th
 e course\, the participants will be able to:\n* Create simple deep-learnin
 g models\n* Identify deep learning parameters\n* Train\, and evaluate a de
 ep-learning auto-encoder model \n* Adapt a pre-existing deep-learning mode
 l to a new task using fine-tuning\n\n\n# Prerequisites\n##### Knowledge / 
 competencies required\n\n* Prior knowledge of ML concepts and methods is r
 equired.\n* A good fluency with the Python programming language\, includin
 g working knowledge of common data analysis libraries such as numpy\, pand
 a\, matplotlib or scikit-learn.\n* Familiarity with different omics data t
 echnologies (highly recommended).\n\n##### Technical\nThe needed libraries
  are indicated in the [dedicated page on the GitHub repo](\nhttps://github
 .com/sib-swiss/deep-learning-practical-training/blob/master/installation_i
 nstructions.md).\n\n\n\n# Application\n**This course is now full with a lo
 ng wating list.**\n\nThe registration fees for academics are **200 CHF** a
 nd **1000 CHF** for for-profit companies.\n\nWhile participants may be reg
 istered on a first come\, first served basis\, exceptions may be made to e
 nsure diversity and equity\, which may increase the time before your regis
 tration is confirmed.\n\nYou will be informed by email of your registratio
 n confirmation. Upon reception of the confirmation email\, participants wi
 ll be asked to confirm attendance by paying the fees within 5 days.\n\nApp
 lications close on *10/10/2024* or as soon as the course is full. Deadline
  for free-of-charge cancellation is set to *25/10/2024*. Cancellation afte
 r this date will not be reimbursed. Please note that participation in SIB 
 courses is subject to our [general conditions](https://www.sib.swiss/train
 ing/terms-and-conditions).\n\n# Venue and Time\nThis course will be stream
 ed. \n\nThe course will start at 9:00 and end around 17:00. \n\nPrecise in
 formation will be provided to the participants in due time.\n\n\n#  Additi
 onal information\nCoordination: Grégoire Rossier\n\nWe will recommend 0.5
  ECTS credits for this course (given a passed exam at the end of the cours
 e).\n\nYou are welcome to register to the SIB courses mailing list to be i
 nformed of all future courses and workshops\, as well as all important dea
 dlines using the form [here](https://lists.sib.swiss/postorius/lists/cours
 es.lists.sib.swiss/).\n\nPlease note that participation in SIB courses is 
 subject to our [general conditions](https://www.sib.swiss/training/terms-a
 nd-conditions).\n\nSIB abides by the [ELIXIR Code of Conduct](https://elix
 ir-europe.org/events/code-of-conduct). Participants of SIB courses are als
 o required to abide by the same code.\n\nFor more information\, please con
 tact [training@sib.swiss](mailto://training@sib.swiss).
SUMMARY:Diving into Deep Learning - Theory and Applications with PyTorch
URL;VALUE=URI:https://www.sib.swiss/training/course/20241108_DEEPP
END:VEVENT
END:VCALENDAR