With the promise of relieving strain on the transport network in maritime cities using Artificial Intelligence and autonomous driving technology, Finnish software powerhouse Reaktor set to build a solution for future waterways. As part of the project, the Valohai platform empowered Reaktor to increase the speed of model development almost tenfold, making it possible to train the self-steering algorithm over night beating the initial training time of one week.
Jacques Marais used machine learning to scan Africa’s elephant population from aerial infrared and color images taken from a plane. The built models were trained first in 2015 with local GPU hardware in three weeks. When the models were retrained in 2017 with the Valohai platform the work was completed in three days while the detection accuracy increased from 56% up to 67% and the overdetection rate dropped dramatically.