Create machine-learning applications for hearing
The hackathon will be organised by the machine-learning applications for hearing and hearing-technology ideas group at the Australian Hearing Hub. The goal is to develop collaborations within the Australian Hearing Hub and across the University, generating grant applications and projects leading to innovative technologies in hearing research.
Prizes 1st Prize: $300 for each challenge 2nd Prize: $150 for each challenge 'People’s Choice’ prize: $100
Challenges There will be two challenges involving data to be released at the start of the hackathon: 1) How well can speech understanding be predicted from electroencephalogram (EEG) data? 2) Can we determine what factors are causing hearing loss in young people, using a dataset of 1400 respondents that includes lifestyle surveys, physiological measurements and hearing tests? We are particularly interested in recruiting hackathon participants with backgrounds in computer science, engineering, statistics, or neuroscience. Some programming experience in Python is recommended. Baseline solutions for the challenges will be provided in Python but participants may approach the problems however they wish.
Structure The hackathon will take place over three days (12-14 December) from 9am to 5pm. Day 1: AM - Icebreaker, introduction to the challenges, form teams PM- Hacking Day 2: Open. For those attending the Australian Hearing Hub, there will be a Python expert at hand to provide support if required. For those working from home or elsewhere, there will be online support throughout the day. Day 3: AM – Hacking PM – presentations, judging and prize giving! Lunch and refreshments will be provided on all three days.