Document Type
Conference Proceeding
Publication Date
10-10-2018
Abstract
Deep neural networks trained over large datasets learn features that are both generic to the whole dataset, and specific to individual classes in the dataset. Learned features tend towards generic in the lower layers and specific in the higher layers of a network. Methods like fine-tuning are made possible because of the ability for one filter to apply to multiple target classes. Much like the human brain this behavior, can also be used to cluster and separate classes. However, to the best of our knowledge there is no metric for how applicable learned features are to specific classes. In this paper we propose a definition and metric for measuring the applicability of learned features to individual classes, and use this applicability metric to estimate input applicability and produce a new method of unsupervised learning we call the CactusNet.
Publication Source (Journal or Book title)
Proceedings of the International Joint Conference on Neural Networks
Recommended Citation
Collier, E., Dibiano, R., & Mukhopadhyay, S. (2018). CactusNets: Layer Applicability as a Metric for Transfer Learning. Proceedings of the International Joint Conference on Neural Networks, 2018-July https://doi.org/10.1109/IJCNN.2018.8489649