AutoMLP
(AI Studio Core)
Synopsis
AutoMLP learner.Description
AutoMLP is a simple algorithm for both learning rate and size adjustment of neural networks during training. The algorithm combines ideas from genetic algorithms and stochastic optimization. It maintains a small ensemble of networks that are trained in parallel with different rates and different numbers of hidden units. After a small, fixed number of epochs, the error rate is determined on a validation set and the worst performers are replaced with copies of the best networks, modified to have different numbers of hidden units and learning rates. Hidden unit numbers and learning rates are drawn according to probability distributions derived from successful rates and sizes. For more information please be kindly referred to the following paper: AutoMLP: Simple, Effective, Fully Automated Learning Rate and Size Adjustment by Thomas Breuel, Faisal Shafait. The Learning Workshop, Cliff Lodge, Snowbird, Utah, United States, Online, 4/2010.
Input
training set (IOObject)
Output
model (AutoMLP)- example set (Data Table)
This is an example set output port
Parameters
- training cyclesThe number of maximum training cycles used for the neural network training.
- number of generationsThe number of generations for AutoMLP training.
- number of esemble mlpsThe number of MLPs per ensemble.