What is Machine Learning & AI?
Machine learning is a sub-area of artificial intelligence. By recognising patterns in existing databases, IT systems are able to independently find solutions to problems.
Machine learning is a sub-area of artificial intelligence. With the help of machine learning, IT systems are able to recognise patterns and laws and develop solutions based on existing data and algorithms. Quasi artificial knowledge is generated from experience. The knowledge gained from the data can be generalised and used for new problem solutions or for the analysis of previously unknown data.
So that the software can learn independently and find solutions, it is necessary for people to act beforehand. For example, the systems must first be supplied with the data and algorithms relevant for learning. In addition, rules for the analysis of the database and the recognition of the patterns must be drawn up. If suitable data is available and rules are defined, systems with machine learning can do the following, among other things:
- Find, extract and summarize relevant data,
- Make predictions based on the analyzed data,
- Calculate probabilities for certain events
- adapt to developments independently and
- Optimize processes based on recognized patterns.
The different types of machine learning
Algorithms play a central role in machine learning. They are responsible for recognizing patterns and generating solutions and can be divided into different learning categories.
- supervised learning
- unsupervised learning
- partially supervised learning
- encouraging learning
- active learning
While with supervised learning example models have to be defined and specified in advance in order to assign the information to the model groups of the algorithms, the model groups with unsupervised learning are automatically created based on independently recognized patterns.
Partially supervised learning is a mixture of both methods. Empowering learning is based on rewards and punishments. This interaction tells the algorithm how to respond to different situations. This way of learning is very similar to human learning.
Finally, active learning offers the algorithm the possibility to request the desired results for certain input data. In order to minimize the number of questions, the algorithm itself selects relevant questions with high relevance to the results.
Depending on the respective system, the database can be available offline or online and can be repeated or only be available once for machine learning. Another distinguishing feature of machine learning is the simultaneous presence of the input and output pairs or their staggered development. Depending on the type, one speaks of batch learning or sequential learning.
Application examples for machine learning
Machine learning has a very wide range of possible applications. In the Internet environment, machine learning is used for the following functions, for example:
- independent detection of spam mails and development of suitable spam filters
- Speech and text recognition for digital assistants
- Determining the relevance of websites for search terms
- Detection and differentiation of internet activity from natural persons and bots
Other areas of application for machine learning are image and face recognition, automatic recommendation services or automatic recognition of credit card fraud.
Big data as a driver of machine learning
The development in the field of big data technology has also given machine learning an enormous boost. Since machine learning requires large amounts of data and must be processed efficiently, big data systems form the ideal basis for this type of learning. With the help of big data, both structured and unstructured data can be analyzed quickly and with relatively little hardware expenditure and fed to the learning algorithms.
Distributed computer structures and particularly fast-working database systems are used for machine learning.
Artificial neural networks that function on the model of the human brain are also used.