RBFA: Radial Basis Function Autoencoders
| Autor: | Michael Mayo, Sally Jo Cunningham, Maisa Daoud |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Similarity (geometry)
business.industry Computer science Gaussian 020208 electrical & electronic engineering Particle swarm optimization 020206 networking & telecommunications Pattern recognition 02 engineering and technology Regularization (mathematics) Autoencoder symbols.namesake Kernel (linear algebra) Transformation (function) Radial function Kernel (statistics) 0202 electrical engineering electronic engineering information engineering symbols Radial basis function Artificial intelligence business |
| Zdroj: | CEC |
| DOI: | 10.1109/cec.2019.8790041 |
| Popis: | We are introducing a new variation of the existing autoencoder called Radial Basis Function Autoencoders (RBFA). This version employs radial symmetric functions, in the first step of encoding, to map the input data vectors into a new form. The transformation which relies on the similarity between the input data examples and predefined center points features forces neurons in the first hidden level to respond similarly to similar patterns of the data. This basic idea of radial transformation (activation) can be interpreted as regularization on the hidden neurons which are penalized based on the similarity criterion so only a fraction of them will become highly activated at one time. The paper also introduces a new method for defining Gaussian radial function’s parameters using Particle Swarm Optimization (PSO). Results indicate that the accuracy of four different classifiers was significantly affected by the number of layers in the first hidden level of the network. RBFA has shown promising results compared to other state of the art autoencoders using different datasets including high-dimensional small-sized medical data. Optimizing the radial function parameters improved the classification accuracy of the four classifiers in some cases. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|