Siemens | Using Machine Learning to Get Machines to Mimic IntuitionSiemens
Building Energy Management System (BEMS)
The capabilities of the latest machine learning systems are illustrated by AlphaGo, with which Google achieved a milestone in the development of self-learning machines and artificial intelligence in March 2016, when AlphaGo succeeded in defeating one of the world’s best Go players: Lee Sedol. The amazing thing is that up until Google’s accomplishment, this Asian strategy game had been considered to be too complex for a computer.
Researchers at Corporate Technology (CT) are studying how machine learning techniques could be used to enable wind turbines to automatically adjust to changing wind and weather conditions, thus boosting their electricity output. The basis for self-optimizing wind turbines is the ability to derive wind characteristics from the turbines’ own operating data. Up until now, this type of data has been used exclusively for remote monitoring and diagnosis; however, this same data can also be used to help improve the electricity output of wind turbines.”
Deep learning techniques are a new trend in machine learning. These techniques utilize up to 100,000 or more simulated neurons and ten million simulated connections —numbers that break all previous records in the field of artificial intelligence. Thanks to their many levels of artificial neurons, whereby each addresses a different level of abstraction of the material to be learned, deep learning techniques are expected, for instance, to enable new applications for automated image recognition.