On regularization properties of artificial datasets for deep learning
| Autor: | Karol Antczak |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Test data generation Computer science Computer Science::Neural and Evolutionary Computation 0211 other engineering and technologies Machine Learning (stat.ML) Economic shortage 02 engineering and technology Machine learning computer.software_genre Regularization (mathematics) Machine Learning (cs.LG) 0203 mechanical engineering Statistics - Machine Learning 021105 building & construction Training set Artificial neural network business.industry Deep learning General Medicine 020303 mechanical engineering & transports Deep neural networks Artificial intelligence business computer |
| Zdroj: | Computer Science and Mathematical Modelling. :13-18 |
| ISSN: | 2450-0054 |
| DOI: | 10.5604/01.3001.0013.6599 |
| Popis: | The paper discusses regularization properties of artificial data for deep learning. Artificial datasets allow to train neural networks in the case of a real data shortage. It is demonstrated that the artificial data generation process, described as injecting noise to high-level features, bears several similarities to existing regularization methods for deep neural networks. One can treat this property of artificial data as a kind of "deep" regularization. It is thus possible to regularize hidden layers of the network by generating the training data in a certain way. 6 pages, 1 figure |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|