Machine learning is typically operated in the cloud, because of the technical elbow room. On mobile devices, resources are extremely limited, which means if you want to run your models directly on the devices, they have to be highly optimized. Tech Crunch brought this interesting news to our attention in their article, “Fritz wants to help developers bring machine learning to their mobile apps.”
This could potentially be a nightmare for mobile developers for many reasons, but a huge one is that different technical giants are using different approaches and different frameworks. This limits or excludes any interoperability.
A new service is working on making this all a bit easier. Fritz offers an end-to-end solution for adding machine learning models to mobile apps and having them run natively on the device. There are apps already using Fritz during the private beta period. PlantVillage, which uses on-device machine learning to detect evidence of crop diseases and gives farmers in East Africa advice for how to treat them, is one.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.