The glossary explains the most important terms relating to artificial intelligence - briefly, clearly and to the point.
A
| Algorithm | A series of rules or steps to solve a problem. |
B
| Bias | Distortions that can arise from unrepresentative or biased data in AI models. |
D
| Data set | A collection of data used to train or test AI models. |
| Deep learning | Specialized area of machine learning based on deep neural networks. |
M
| Machine Learning | Sub-area of AI in which algorithms learn from data. |
N
| Natural Language Processing | AI field that deals with the processing and analysis of natural language. |
| Neural network | Model inspired by the human brain, which is used for data processing. |
O
| Overfitting | Problem where a model fits the training data too accurately but performs poorly on new data. |
P
| Prompt | An input or instruction given to an AI model such as ChatGPT to obtain a desired response. Can consist of text, questions, commands or context and controls how the AI responds or what information it provides. |
S
| Speech-to-Text (STT) | Refers to the technology that converts spoken language into written text. It is used, for example, in speech recognition systems, digital assistants or transcription services. |
T
| Text Simplification | Refers to the process of converting a complex text into a simpler, easier-to-understand version. Difficult words, long sentences or complex structures are simplified without changing the original content or meaning. |
| Text-to-Speech (TTS) | Refers to the technology that converts written text into spoken language. It is used, for example, in voice assistants, navigation systems or reading apps. |
| Training | The process by which an AI model learns from data. |
Was this helpful?
0 / 0