| Dropout Layer |
A neural network layer that switches off some neurons at random during training to reduce overfitting and improve model robustness. |
| Edge AI |
AI that runs locally on local devices such as smartphones or cameras, enabling fast results without the need to send data to a central server. |
| Edge Computing |
When computing processes data directly where it's created, such as on local devices, rather than sending it to a remote server, making things faster and less reliant on the internet. |
| Ensemble Learning |
A machine learning strategy in which numerous models are integrated to increase overall performance, resulting in more accurate predictions than a single model alone. |
| Ethical AI |
Ethical AI involves developing and deploying AI systems in a fair, transparent, and responsible manner that avoids harm, bias, and discrimination, while also respecting privacy and human rights. |
| ETL |
ETL (Extract, Transform, Load) is a data management process in which data is extracted from various sources, transformed into an appropriate format, and then put into a database or data warehouse for analysis. |
| Expert System |
A computer software that simulates a human expert's decision-making skill by applying a set of rules and knowledge to solve specific problems in fields such as medical, economics, and engineering. |
| Explainability |
The ability to grasp and explain how an AI model makes its judgments, making its processes transparent and interpretable for people, and assuring trust and responsibility. |
| Explainable AI (XAI) |
Artificial intelligence systems that make their decision-making processes transparent and understandable, allowing consumers to better understand how and why a particular choice was made, hence boosting trust and accountability. |
