BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260615T003439Z UID:b500d53d-1a75-4f93-9203-4285ee7f8905 DTSTART:20190909T090000Z DTEND:20190913T170000Z DESCRIPTION:Educators:\nFlorian Jug\, Peter Steinbach\, others (DAIS/CIBI)\ n\nDate:\n09.09.2019 – 13.09.2019\n\nLocation:\nSLUB\, Klemperer-Saal\nZ ellescher Weg 18\n01069 Dresden\nGermany\n\nContents:\nThe Dresden Deep Le arning Hackathon ( #d3hack2019 ) is meant to bring together machine learni ng experts and scientific practitioners. Teams of 2-4 scientists can apply for the hackathon given a scientific problem they want to solve with mach ine learning. Upon approval\, they will be assisted by one or two machine learning experts for 5 days consecutively! This effort is meant to give yo ur team a head-start and potentially create an end-to-end machine learning solution for your science. The teams are motivated to publish a scientifi c paper about the hackathon efforts at dedicated conferences or in establi shed journals - at best jointly with their mentors - after the hackathon. A win-win situation for all parties involved. \n\nThe scope of scientific domains that can apply is not limited. For sure\, our mentors have a given background mostly with regard to 2D or 3D images. So we will try to match that as close as possible. However\, we are still in the process of fixin g mentors (we have expressions of interest of about 5 more than listed bel ow). We will also consider a limited amount of applications using standard machine learning (MLP\, SVM\, RandomForests\,...).\nIf you are unclear wh ether your topic fits the hackathon\, please reach out to us.\n\nMost impo rtantly\, any team without a readily available data set for training will be discarded from the candidate list. In other words\, if you are interest ed in applying machine learning to your data\, you shouldn't use the hacka thon to annotate your data.\n\nThe workshop admission fee amounts to € 3 00 per participant to cover room rent and catering. We are still looking f or sponsors\, so there is a non-negligible probability that the admission fee will be reduced in the future.\n\nThe call for applications closes on June 30\, 2019\, at 12pm AoE! After this date\, a review board of mentors and organizers will judge the applications and send out confirmations to t he applications until mid July the latest. The registration mechanism of p articipants will be circulated then.\n\nFor members of non-academic instit utions: We cannot allow applications from non-academic institutions or ind ustry to our hackathon. If you want to participate with a project as a com pany\, this project needs to be embedded in a scientific group and the maj ority of team members need to be employed by a scientific institution. On top\, the results of the hackathon are expected to be published. So be pr epared to undisclose your results and (at best) the data and code which pr oduced these results.\n\n\nLearning goals:\n- Fundamentals of deep learnin g with CNNs.\n- Keras API with the Tensorflow backend.\n- How to define yo ur deep net.\n- How to train it.\n\nPrerequisites:\nBring your own laptop. Keras and Tensorflow backend should already be installed. (We will have G PU nodes you can use if your laptop does not offer a fast GPU.) Solid unde rstanding of the fundamentals of linear algebra. Programming skills (never programmed… that will not work out\, sorry!)\n\nKeywords:\nDeepLearning \, Keras\, Tensorflow\, Python\n\nTools:\nKeras\, Python\, Tensorflow LOCATION:Dresden SUMMARY:Dresden Deep Learning Hackathon URL;VALUE=URI:https://www.denbi.de/training/636-dresden-deep-learning-hacka thon END:VEVENT END:VCALENDAR