Research on the Classification Ability of Deep Belief Networks on Small and Medium Datasets
| Autor: | Andrey Bondarenko, Arkady Borisov |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Vanishing gradient problem
Artificial neural network Artificial neural networks Computer science deep belief networks Boltzmann machine computer.software_genre Net (mathematics) Backpropagation Data set Deep belief network classification restricted Boltzmann machines Unsupervised learning Data mining computer |
| Zdroj: | Information Technology and Management Science; Vol 16, No 1 (2013): Information Technology and Management Science; 60-65 |
| ISSN: | 2255-9086 2255-9094 |
| Popis: | Recent theoretical advances in the learning of deep artificial neural networks have made it possible to overcome a vanishing gradient problem. This limitation has been overcome using a pre-training step, where deep belief networks formed by the stacked Restricted Boltzmann Machines perform unsupervised learning. Once a pre-training step is done, network weights are fine-tuned using regular error back propagation while treating network as a feed-forward net. In the current paper we perform the comparison of described approach and commonly used classification approaches on some well-known classification data sets from the UCI repository as well as on one mid-sized proprietary data set. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|