Abstract:

Over the past decade, machine learning has been applied to many areas of technology, including speech recognition in acoustic signals, object and face recognition in images, document analysis or stock market quote prediction. Many of the solutions mentioned have found real application in business. In each case mentioned, the use of idealised models or mathematical equations did not have the desired effect. It was not until the use of large sets of real-world data, combined with machine learning, that the technology to detect and analyse complex data like human speech and photographs evolved. RF (Radio Frequency) systems are also still designed using mathematical equations and models, based on idealised assumptions and approximations about the problem, equipment and operating environment.