neural networks research group
areas
people
projects
demos
publications
software/data
Faster Training by Selecting Samples Using Embeddings (2019)
Santiago Gonzalez
, Joshua Landgraf, and
Risto Miikkulainen
Long training times have increasingly become a burden for researchers by slowing down the pace of innovation, with some models taking days or weeks to train. In this paper, a new, general technique is presented that aims to speed up the training process by using a thinned-down training dataset. By leveraging autoencoders and the unique properties of embedding spaces, we are able to filter training datasets to only include only the samples that matter the most. Through evaluation on a standard CIFAR-10 image classification task, this technique is shown to be effective. With this technique, training times can be reduced with a minimal loss in accuracy. Conversely, given a fixed training time budget, the technique was shown to improve accuracy by over 50%. This intelligent dataset sampling technique is a practical tool for achieving better results with large datasets and limited computational budgets.
View:
PDF
Citation:
In
Proceedings of the 2019 International Joint Conference on Neural Networks
, 1-7, Budapest, Hungary, July 2019.
Bibtex:
@article{gonzalez:ijcnn19, title={Faster Training by Selecting Samples Using Embeddings}, author={Santiago Gonzalez and Joshua Landgraf and Risto Miikkulainen}, booktitle={Proceedings of the 2019 International Joint Conference on Neural Networks}, month={July}, address={Budapest, Hungary}, pages={1-7}, url="http://nn.cs.utexas.edu/?gonzalez:ijcnn19", year={2019} }
People
Santiago Gonzalez
Ph.D. Alumni
slgonzalez [at] utexas edu
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Unsupervised Learning, Clustering, and Self-Organization
Other Areas