BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//SciLifeLab - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:SciLifeLab
X-ORIGINAL-URL:https://www.scilifelab.se
X-WR-CALDESC:Events for SciLifeLab
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20220327T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20221030T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20231029T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20230320T090000
DTEND;TZID=Europe/Stockholm:20230324T170000
DTSTAMP:20260404T190343
CREATED:20221026T132922Z
LAST-MODIFIED:20230306T114543Z
UID:144889-1679302800-1679677200@www.scilifelab.se
SUMMARY:NBIS workshop in Neural Nets and Deep Learning
DESCRIPTION:National course open for PhD students\, postdocs\, researchers and other employees in need of Neural networks and Deep Learning skills within all Swedish universities. \n\n\n\n\n\n\n\nImportant dates\n\n\n\nApplication opens: 2022-10-25 \n\n\n\nApplication closes: 2023-02-10 \n\n\n\nConfirmation to accepted students:  2023-02-17 \n\n\n\nResponsible teachers:  Claudio Mirabello\, Christophe Avenel \n\n\n\nIf you do not receive information according to the above dates please contact: edu.neural-nets-deep-learning@nbis.se \n\n\n\nCourse webpage\n\n\n\nApplication\n\n\n\n\n\n\n\nCourse fee\n\n\n\nA course fee* of 2200 SEK will be invoiced to accepted participants. This includes lunches\, coffee and snacks. \n\n\n\n*Please note that NBIS cannot invoice individuals \n\n\n\n\n\n\n\nCourse content\n\n\n\nThis course will give an introduction to the concept of Neural Networks (NN) and Deep Learning. \n\n\n\nTopics covered will include: \n\n\n\n\nNN building blocks\, including concepts such as neurons\, activation functions\, loss functions\, gradient descent and back-propagation\n\n\n\nConvolutional Neural Networks\n\n\n\nRecursive Neural Networks\n\n\n\nAutoencoders\n\n\n\nBest practices when designing NNs\n\n\n\n\n\n\n\n\nLearning outcomes\n\n\n\nUpon completion of this course\, you will be able to: \n\n\n\n\nDistinguish the concepts of “Artificial Intelligence”\, “Machine Learning”\, “Neural Networks”\, “Deep Learning”\n\n\n\nDistinguish between different types of learning (e.g. supervised\, unsupervised\, reinforcement) and recognise which applies to their own problem\n\n\n\nDistinguish between linear and non-linear approaches and recognise which is best suited for application to their own problem\n\n\n\nDescribe what a feed-forward neural network (FFNN) is\, along with its components (neurons\, layers\, weights\, bias\, activation functions\, cost functions)\n\n\n\nExplain how training of a FFNN works from a mathematical point of view (gradient descent\, learning rate\, backpropagation)\n\n\n\nExecute with pen and paper a few steps of training of a very simple FFNN model\n\n\n\nTell the difference between a shallow and a deep network\n\n\n\nExplain broadly how different NN architectures are wired and how they work\n\n\n\nImplement and apply the most appropriate architecture to a given problem/dataset\n\n\n\nAnalyze training curves and prediction outputs to evaluate if the training has been successful\n\n\n\nDebug possible issues with the training and suggest changes to fix them\n\n\n\nExplain the difference between training\, validation and testing\n\n\n\nDefine what overfitting is from a mathematical point of view\, and what issues it causes\n\n\n\nIdentify what constitutes good practices of dataset design and how to avoid introducing information leakage or other biases when building their own datasets\n\n\n\n\n\n\n\n\nEntry requirements\n\n\n\nRequired for being able to follow the course and complete the computer exercises: \n\n\n\n\nFamiliarity with Unix/Linux\n\n\n\nAbility to bring your own laptop with Python and Jupyter Notebooks  installed for the practical exercises\n\n\n\nProgramming/scripting experience in Python (e.g. having attended the NBIS workshop in basic Python or equivalent)\n\n\n\nBasic experience of statistics and mathematics (e.g. having attended the NBIS workshop Introduction to Biostatistics and Machine Learning or equivalent)\n\n\n\n\nDesirable: \n\n\n\n\nYou have experience of working with Jupyter Notebooks\n\n\n\nYou have a necessity  to work with large datasets (e.g. thousands of samples)\n\n\n\n\n\n\n\n\nDue to limited space the course can accommodate a maximum of 25 participants. If we receive more applications\, participants will be selected based on several criteria. Selection criteria include correct entry requirements\, motivation to attend the course as well as gender and geographical balance.
URL:https://www.scilifelab.se/event/nbis-workshop-in-neural-nets-and-deep-learning-2/
LOCATION:Navet\, SciLifeLab Uppsala\, SciLifeLab Uppsala\, BMC C11\, Husargatan 3\, Uppsala\, 75237\, Sweden
CATEGORIES:Course
ORGANIZER;CN="NBIS - National Bioinformatics Infrastructure Sweden":MAILTO:education@nbis.se
END:VEVENT
END:VCALENDAR