TRANSFER LEARNING FOR TRAINING ACCELARATION

Autor: Ilmārs Apeināns, Vitālijs Žukovs, Sergejs Kodors, Imants Zarembo
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Zdroj: HUMAN. ENVIRONMENT. TECHNOLOGIES. Proceedings of the Students International Scientific and Practical Conference; No 25 (2021): Human. Environment. Technology; 16-21
ISSN: 2592-8597
Popis: In this work, authors compare training time of standard convolution neuron network model with model trained using transfer learning. Both models are based on Alexnet architecture. CNN model training from scratch included full model, but using transfer learning, some layers of model were frozen for learning acceleration considering transfer learning methodology.
Databáze: OpenAIRE