If you have an activation function that is so close to being on the edge, that the precision causes it to go the wrong way, then the direction it goes is probably not terribly important. However, the "more resources are cheap" argument is probably not true even for some offline scanning because a lot of OCR applications wind up having massive throughput, so the impact is considerable, especially when you likely will not have a single error occur as a result of this change.
When I worked in document management (left that in early 2015), there were a lot of things that were not very time-sensitive like your experience, but there are many other uses of OCR such as live translation, sorting into immediate routing logic, etc. I don't know how I would get a reasonable estimate of who does care about resources, but I'm sure there are a lot of applications that do something immediately and interactively with the input. The performance, on the other hand, is not only measurable but pretty significant. This is in most cases MUCH cheaper than dealing with recognition errors in the long term.The difference in accuracy is probably too small to measure even on a massive scale. If performace would actually become a real pita, I would simply provide more computing power. I archive a lot of paper, and I don't care how much processing time the recognition process takes at all. Though I of course appreciate any performance gain, in this case I just care for the quality of the results of the recognition process.Ī lot of use cases aren't even real time critical. Okay, it has become faster by using float instead of double.
0 kommentar(er)
