Infothek

This page contains automatically translated content.

09/11/2023 | Intelligent Embedded Systems

New paper accepted for the Work­shop In­ter­ac­tive Ad­ap­ti­ve Learning (IAL), ECML PK­DD 2023

The paper titled "Role of Hyperparameters in Deep Active Learning" by Denis Huseljic, Marek Herde, Paul Hahn, and Bernhard Sick addresses the often overlooked problem of selecting appropriate training hyperparameters (HPs), such as learning rate, that play a crucial role in how deep neural networks learn during each training cycle. This study shows that optimizing these hyperparameters can help reduce the performance differences between different DAL strategies. 

News

09/11/2023 | Intelligent Embedded Systems

New paper accepted for the Work­shop In­ter­ac­tive Ad­ap­ti­ve Learning (IAL), ECML PK­DD 2023

The paper titled "Role of Hyperparameters in Deep Active Learning" by Denis Huseljic, Marek Herde, Paul Hahn, and Bernhard Sick addresses the often overlooked problem of selecting appropriate training hyperparameters (HPs), such as learning rate, that play a crucial role in how deep neural networks learn during each training cycle. This study shows that optimizing these hyperparameters can help reduce the performance differences between different DAL strategies. 

Dates

Back
09/11/2023 | Intelligent Embedded Systems

New paper accepted for the Work­shop In­ter­ac­tive Ad­ap­ti­ve Learning (IAL), ECML PK­DD 2023

The paper titled "Role of Hyperparameters in Deep Active Learning" by Denis Huseljic, Marek Herde, Paul Hahn, and Bernhard Sick addresses the often overlooked problem of selecting appropriate training hyperparameters (HPs), such as learning rate, that play a crucial role in how deep neural networks learn during each training cycle. This study shows that optimizing these hyperparameters can help reduce the performance differences between different DAL strategies.