Skip to content

Latest commit

 

History

History
29 lines (23 loc) · 2.16 KB

README.md

File metadata and controls

29 lines (23 loc) · 2.16 KB
Raw

Mozgalo 2018. Competition - Robust Machine Learning Challenge

About Mozgalo

Mozgalo is the first and the only Croatian competition for students in Data mining and Big Data.

Through their solutions, students gather useful knowledge and information among big amounts of structured and unstructured data. They use different statistical techniques, machine learning and computer vision algorithms. One of Mozgalo’s primary goals is to encourage students to do analytical thinking, prediction modeling and independently develop their own creative solutions to real problems using their knowledge of computer science, statistics and mathematics. In addition to that, students develop their communication and business skills, teamwork and they have an opportunity to connect with companies from IT and bank sector. During the competition, educational workshops are being held and competitors are offered mentorship and online educational content. The competition is opened to all students, in teams of 2 to 4 people.

Data mining and predictive models are foundations of successful business in multiple industries and therefore this area can be considered the profession of the future.

Task

Strojno učenje je u zadnjih nekoliko godina u području računalnog vida napravilo svojevrsnu revoluciju. Na nekim javno dostupnim skupovima podataka postižu se rezultati bolji od čovjeka što ukazuje na veliki potencijal za ozbiljnu industrijsku primjenu. S druge strane, u praksi je razvijanje konkretnih rješenja često znatno kompleksnije zbog dodatnih zahtjeva i ograničenja. Cilj ovogodišnjeg Mozgala je upoznati studente s izazovima razvijanja robusnih rješenja strojnog učenja. Zadatak je u teoriji jednostavan problem klasifikacije slike koji u praksi postaje vrlo zahtjevan. Konkretno, radi se o klasifikaciji slika računa trgovačkih centara na temelju njihovih vidljivih logo obilježja. Timovi će na označenom skupu od ukupno 45 000 slika i 25 različitih klasa razvijati rješenje čija će se robusnost mjeriti na skupu slika koje simuliraju stvarne uvjete industrijske primjene.

Team

  • Team name: EuroNeuro
  • Members:
    • Bartol Freškura
    • Filip Gulan
    • Damir Kopljar