RapidMiner Extension: AutoMLP

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.

You can find more details in the the following publications:

Pattern Recognition Engineering
AutoMLP: Simple, Effective, Fully Automated Learning Rate and Size Adjustment

You can download it from here:

AutoMLP (zip)

Just unzip the AutoMLP.zip and copy the AutoMLP.jar file into the lib/plugins/ folder within your RapidMiner installation. Then restart RapidMiner and the extension will be loaded automatically.

You can find the AutoMLP Operator in the Operator tree in Modeling ⇒ Classification and Regression ⇒ Neural Net Training .