IrisConsole

Neural network example with Delphi + FANN (Fast Artificial Neural Network Library) under MS Windows. Solves Iris flowers classification problem (Fisher, 1936) with two methods:

1. Neural network classification (output layer with three neurons, one neuron per class).
2. Neural network "tricky" regression (output layer with single neuron).

Iris data set is included. Normalization has been implemented. For "tricky" regression, all 6 permutations of three output labels has been tried.

Requires

• Delphi 10.3 Community Edition or Delphi 10.2 Tokyo Starter Edition - Download
• Delphi FANN 2.1 (actually fann_delphi_2_0) - Download

Download IrisConsole from GitHub™

• https://github.com/pcbua/IrisConsole