Table 4 Common types of ANN
From: Machine learning methods for predicting residual strength in corroded oil and gas steel pipes
Type | Outline |
|---|---|
FFNN | Modeling of input and output data through certain relationships75. |
BRANN | Improving model generalization by reducing network weights61. |
BPNN | A type of feedforward neural network that utilizes error backpropagation104. |
RBFNN | Hidden layers use radial basis functions for nonlinear mapping13. |
ANFIS | Combining the learning capabilities of neural networks with the interpretability and reasoning capabilities of fuzzy logic systems59. |
ELM | Accelerating the training process of neural networks by randomly initializing their hidden layer weights and biases112. |
MLP | Incorporating multi-level, nonlinear mapping and adjusting weights through backpropagation enables the management of complex data relationships and the effective learning of various machine learning tasks75. |
DELM | Combining the concept of extreme learning machines with the architecture of deep neural networks77. |
