Optimizing neural networks for parameter efficiency
No Thumbnail Available
Files
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
Sumy State University
Bachelor’s paper
Date of Defense
Scientific Director
Speciality
Date of Presentation
June 2024
Abstract
An algorithm for optimizing the correspondence of the neural network model to the training data was proposed. The performance criteria of the neural network in the training and validation set are defined. The algorithm is implemented in software, which provides a better understanding of the step-by-step process of learning the model and implementing the optimization algorithm.
Keywords
neural network, training set, validation set, validation loss, training loss
Citation
Ude V. S. Optimizing neural networks for parameter efficiency : bachelor's qualification work : specialty 122 – сomputer science / head V. A. Kolesnikov. Sumy : Sumy State University, 2024. 33 p.