DT: Function shaping in deep learning. Cover

Function shaping in deep learning

Doctoral Thesis

Ēvalds Urtāns, Riga Technical University, Latvia

ORCID iD https://orcid.org/0000-0001-9813-0548

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

Defence date

01.12.2021.

Format

Pages

165

Published online

Publication language

Publisher

RTU Press

Country of Publication

Latvia

Reviews

There are no reviews yet.

Be the first to review “Function shaping in deep learning. Doctoral Thesis”