Глоссариум по искусственному интеллекту: 2500 терминов. Том 2

Training on a disproportionately low percentage of over-represented class examples in order to improve model training on under-represented classes. For example, in a class-imbalanced dataset, models tend to learn a lot about the majority class and not enough about the minority class. Downsampling helps balance the amount of training on the majority and minority classes[426 - Downsampling [Электронный ресурс] https://developers.google.com

https://developers.google.com/machine-learning/glossary#downsampling (дата обращения: 09.

04.2023)].

Driver is computer software that allows other software (the operating system) to access the hardware of a device[427 - Драйвер [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Драйвер (дата обращения: 09.04.2023)].

Drone – unmanned aerial vehicle (unmanned aerial system)[428 - Дрон [Электронный ресурс] https://ru.wikipedia.org URL: https://ru.wikipedia.org/wiki/Беспилотный_летательный_аппарат (дата обращения: 09.

04.2023)].

Dropout regularization is a form of regularization useful in training neural networks. Dropout regularization works by removing a random selection of a fixed number of the units in a network layer for a single gradient step. The more units dropped out, the stronger the regularization[429 - Dropout regularization [Электронный ресурс] https://developers.google.com URL: https://developers.google.com/machine-learning/glossary#dropout-regularization (дата обращения: 30.

06.2023)].

Dynamic epistemic logic (DEL) is a logical framework dealing with knowledge and information change. Typically, DEL focuses on situations involving multiple agents and studies how their knowledge changes when events occur[430 - Dynamic epistemic logic [Электронный ресурс] https://en.wikipedia.org URL: https://en.wikipedia.org/wiki/Dynamic_epistemic_logic (дата обращения: 09.04.2023)].

Dynamic model is a model that is trained online in a continuously updating fashion.

That is, data is continuously entering the model[431 - Dynamic model [Электронный ресурс] https://www.primeclasses.in URL: https://www.primeclasses.in/glossary/data-science-course/machine-learning/dynamic-model (дата обращения: 09.04.2023)],[432 - Динамическая модель [Электронный ресурс] https://kartaslov.ru URL: https://kartaslov.ru/карта-знаний/Динамическая+модель (дата обращения: 09.04.2023)].