Hizalama
The effort of artificial intelligence systems to act harmoniously with human values and intentions.
Alignment research aims to ensure models act useful, harmless and honest; prevent unwanted or dangerous behavior.
A Harfi
👁 36 views
Other terms from the letter "A"
A
A
A
A
Adversarial Attack
The method of adding small, intentional changes, as soon as a model will not be …
Attention Mechanism
The mechanism that determines which parts of the input will focus more on when p…
AI Agent
The presence of software that detects, decides and actions to achieve a specific…
Activation Function
Function that determines the output of a neuro, non-linearity to the network.