Multiobjective Deep Learning
Published in University of California, Los Angeles on 2019
Recommended citation: Jayanth, Jayanth. Multiobjective Deep Learning. University of California, Los Angeles, 2019. https://escholarship.org/content/qt3ww3r9m2/qt3ww3r9m2.pdf
Many current challenges in natural language processing and computer vision have to deal with multiple objectives simultaneously. In this article, we study different methods to solve such multi-objective problem for CIFAR-100 and SEMEVAL datasets, and compare with traditional deep learning methods. The multi-output method achieves better results than training a single neural net from scratch with its own model for each objective. Multi-objective deep learning with weights achieves comparable results too.