Machine learning especially deep learning are the core competences of Artificial Intelligence. Self-learning programs are being used today in increasingly more products and solutions. Machine-learning algorithms can be found in speech recognition applications on smartphones as well as in spam filters in anti-virus programs. Personalised online advertising also only works as well as it does because of learning systems. A whole range of different concepts, methods and theoretical approaches is involved in this context. Yet all have one goal in common: the computer or the machine should acquire empirical knowledge independently and, based on this find solutions autonomously for new and unknown problems. This makes machine learning one of the core fields of Artificial Intelligence, without which other core competences of smarter systems, such as pattern recognition or natural-language processing, would scarcely be conceivable. The technology is actually not especially new, with AI pioneer Marvin Minsky already developing an initial learning machine in the 1950s. However, the breakthrough and practical application of the relevant methods really only came about owing to rapid development in recent years in the area of semiconductor technology. Except that with the processor technology now available, it was possible to process large volumes of data at high speed in parallel.
Many experts regard this area as currently having the greatest potential within AI.
Deep learning currently dominates learning methods
Deep learning is a method of machine learning: many experts regard this area as currently having the greatest potential within AI. Deep learning uses complex neural networks to learn autonomously how something can be classified. The system records large volumes of known information – for example pictures or sounds – in a database and compares it with unknown data.
The procedure eliminates many work steps involved in classic machine learning. That’s because the training effort is significantly less: the “trainer” simply has to present the neural network with data such as pictures – the system discovers for itself how the objects shown in the pictures are to be classified. The human has to unambiguously indicate whether the object whose recognition is to be learned can be seen in the picture (therefore, for example, whether or not a pedestrian is shown in the picture). The deep-learning program uses the information from the training data in order to define typical features of a pedestrian and generate a prediction model from this. The system works down deeper into the neural network level by level – hence the name deep learning. The nodes at the first level, for example, only register the brightness values of the image pixels. The next level recognises that some of the pixels form lines. The third differentiates between horizontal and vertical lines. This iterative process continues until the system recognises legs, arms and faces and has learned how a person in the picture should be classified.
This learning process requires significant computing power, however, and therefore places increased demands on the processor technology. Researchers and manufacturers are consequently working intensively on developing special AI chips that can perform even more computing processes faster.
Simply a case of sharing acquired knowledge
At the same time, thought is being given as to how the knowledge that a system has elaborately acquired can be made available to other systems, too. This would then mean, for example, that not every autonomous vehicle would have to learn for itself what a pedestrian looks like, rather it could draw on the experience of vehicles that have been on the road for longer. The Khronos Group, an open consortium of leading hardware and software companies presented an exchange format for neural networks at the end of 2017. The Neural Network Exchange Format 1.0 allows scientists and engineers to transfer existing trained networks from the training platform to a host of other systems – in other words, in the same way as with PDF format in text processing.