CactusNets: Layer Applicability as a Metric for Transfer Learning
| Autor: | Edward Collier, Robert DiBiano, Supratik Mukhopadhyay |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer science Feature extraction Machine Learning (stat.ML) 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Machine Learning (cs.LG) Statistics - Machine Learning 0202 electrical engineering electronic engineering information engineering Layer (object-oriented design) 0105 earth and related environmental sciences Artificial neural network business.industry Filter (signal processing) Computer Science - Learning Metric (mathematics) Task analysis Unsupervised learning 020201 artificial intelligence & image processing Artificial intelligence Transfer of learning business computer |
| Zdroj: | IJCNN |
| DOI: | 10.48550/arxiv.1804.07846 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|