AI technology is, therefore, complex.ĪI-related risks regularly make news headlines, may cause significant reputation damage, and have led to a number of legislative initiatives and ethical frameworks in the areas of privacy, fair and equal treatment, and fair competition. Sometimes the mistakes are even hard to notice.īecause blackboxness is bad English we will call it a complexity problem instead, keeping in mind that we do not have an objective measure of topological complexity in mind, but rather our inability to simulate what it does. And it does make mistakes that humans will never make. But its design specification does not lend itself to simulation of its behavior in our mind: the relation between input and output data is discovered by the AI technology itself. It sometimes surprises us by finding predictive patterns in data we did not see. It may have some capacity to adapt to changes in its environment. It has, in essence, a blackboxness problem. Popularly, AI technology is positioned somewhere between humans and computers.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |