Dr Chris Hines1
1Monash Eresearch Centre, Clayton, Australia
Neural Networks are the new hawtness in machine learning and more generally in any field that relies heavily on computers and automation. Many people feel its promise is overhyped, but there is no denying that the automated image processing available is astounding compared to ten years ago. While the premise of machine learning is simple, obtaining a large enough labeled dataset, creating a network and waiting for it to converge before you see a modicum of progress is beyond most of us. In this talk I consider a hypothetical automated kiosk called “Beerbot”. Beerbot’s premise is stated simply: keep a database of how many beers each person has taken from the beer fridge. I show how existing open source published networks can be chained together to create a “good enough” solution for a real world situation with little data collection or labeling required by the developer and no more skill than a bit of basic python. I then consider a number of research areas where further automation could significantly improve “time to science” and encourage all eResearch practitioners to have a go.
Biography:
Chris has been kicking around the eResearch sector for over a decade. He has a background in quantum physics and with the arrogance of physicists everywhere things this qualifies him to stick his big nose into topics he knows nothing about.