GP-Based Kernel Evolution for L2-Regularization Networks

The paper details a genetic programming procedure for evolving an optimal kernel for an L2-Regularization Network. Is has been presented at the 2014 IEEE Congres on Evolutionary Computation: see paper on IEEEXplore. Below you will find the instructions to repeat the experiments in the paper. If you use this code or any derivation of it in your research, please cite the paper as:

Step 1 – Install Lynx

Download the latest version from the master branch of the toolbox:

https://github.com/ispamm/Lynx-Toolbox/

After downloading it, install it using the “install” script in the root folder. Refer to Chapter 3 of the user manual for more information on the guided procedure.

Step 2 – Define the configuration

Lynx works by specifying the details of a simulation in a configuration file. To this end, create a file named “config_gp.m” in the “configs” folder, with the following code:

Step 3 – Run the simulation

Run the simulation with the “run_simulation” script, by selecting the configuration file created at step 2. You can modify the dataset at line 14, other datasets that have been used in the paper are “uci_glass”, “uci_wdbc” and “uci_yacht”. They are all included in the toolbox. Please refer to Section 3.1 of the user manual for details on the syntax of the function “add_dataset”. If you use another dataset, remember to set the parameters of the model accordingly, details on the optimal parameters can be found in Table IV of the paper.