Funkciju formēšana dziļajā mašīnmācīšanā
Promocijas darba kopsavilkums
Ēvalds Urtāns, Riga Technical University, Latvia
This work describes the importance of loss functions and related methods for deep reinforcement learning and deep metric learning. A novel MDQN loss function outperformed DDQN loss function in PLE computer game environments, and a novel Exponential Triplet loss function outperformed the Triplet loss function in the face re-identification task with VGGFace2 dataset reaching 85,7 % accuracy using zero-shot setting. This work also presents a novel UNet-RNN-Skip model to improve the performance of the value function for path planning tasks.
Additional information
Publication type | |
---|---|
DOI | |
Defence date | 01.12.2021. |
Format | |
ISBN (pdf) | 978-9934-22-684-7 |
Pages | 76 |
Published online | |
Publication language | |
Publisher | RTU Press |
Country of Publication | Latvia |
You must be logged in to post a review.
Reviews
There are no reviews yet.