ANNs are networks of artificial neurons and have a biological blueprint. Leaning on biology, an artificial neuron is an object that reacts to one or more stimuli, depending on how strongly it is activated or the stimulus is weighted. An ANN basically consists of an input layer and an output layer. In between are hidden layers or activity layers. As a rule, ANNs need to be trained before they can solve problems. In the process, a certain algorithm or the neural network weights the connections of the neurons on the basis of predefined learning material and learning rules until it has reached or developed a certain learning goal.
See also:ETSI GR ENI 004 computing system that learns to perform functions by using artificial neurons that take the form of a directed, weighted graph.
NOTE: An ANN learns to perform a function by analysing examples (i.e. training data) instead of being programmed to perform a task.
The term is discussed in various disciplines from different perspectives. Due to the AI effect, the term is constantly evolving. Three definitions are given below:
Definition 1:
Capability of an engineered system to acquire, process and apply knowledge and skills (ISO/IEC 29119-11).
Definition 2:
Computerized system that uses cognition to understand information and solve problems (ISO/IEC 22989).
Definition 3:
Artificial intelligence refers to a set of technologies [...]
that, for a given set of human-defined objectives, generate outputs such as content, predictions, recommendations, or decisions influencing the environments they interact with (European AI Act in draft 1).
-
AI-Act (Regulation of the European Parliament and of the Council Laying Down Harmonised Rules on Artificial Intelligence (Artificial Intelligence Act), Volltext auf Europa.eu ↩︎
ETSI GR ENI 004 computerized system that uses cognition to understand information and solve problems
NOTE 1: ISO/IEC 2382-28 defines AI as "an interdisciplinary field, usually regarded as a branch of computer science, dealing with models and systems for the performance of functions generally associated with human intelligence, such as reasoning and learning".
NOTE 2: In computer science AI research is defined as the study of "intelligent agents": any device that perceives its environment and takes actions to achieve its goals.
NOTE 3: This includes pattern recognition and the application of machine learning and related techniques.
NOTE 4: Artificial Intelligence is the whole idea and concepts of machines being able to carry out tasks in a way that mimics the human intelligence and would be considered "smart".
ISO/IEC DIS 22989 set of methods or automated entities that together build, optimize and apply a model (3.1.26) so that the system can, for a given set of predefined tasks (3.1.37), compute predictions (3.2.12), recommendations, or decisions.
Note 1 to entry: AI systems are designed to operate with varying levels of automation (3.1.7).
Note 2 to entry: Predictions (3.2.12) can refer to various kinds of data analysis or production (including translating text, creating synthetic images or diagnosing a previous power failure). It does not imply anteriority. study of theories, mechanisms, developments and applications related to artificial intelligence (3.1.2).
ISO/IEC TR 29119-11:2020 capability of an engineered system to acquire, process and apply knowledge and skills
ISTQB - CTAI Syllabus The capability of an engineered system to acquire, process, create and apply knowledge and skills (ISO/IEC TR 29119-11)
Node in an artificial neural network (ANN) that receives weighted input data and subsequently generates outputs based on usually non-linear functions.
ETSI GR ENI 004 node in an ANN that receives weighted input data, adds the data, and produces an output using a non-linear output function.
NOTE: The output function is also called a transfer function or activation function, and represents what portion of the potential action is transmitted.
ISO/IEC DIS 22989 primitive processing element which takes one or more input values and produces an output value by combining the input values and applying an activation function on the result.
Note 1 to entry: Examples of nonlinear activation functions are a threshold function, a sigmoid function and a polynomial function.
ISTQB - CTAI Syllabus neuron: A node in a neural network, usually receiving multiple input values and generating an activation value