Feed Forward Single/Multiple-Hidden Layer Classifier for Thyroid Dataset
Python (sklearn-based) implementation that explores how different parameters impact a feed-forward neural network with single/multiple hidden layers.
A brief analysis of the results is provided in Portuguese. It was submitted as an assignment of a graduate course named Connectionist Artificial Intelligence at UFSC, Brazil.
In short, two normalization methods are evaluated (minmax and Yeo-Johnson) in a thyroid dataset from UCI ported to matlab with multiple training algorithms, hidden layers, learning rate (alpha), epochs and activation functions.
| Before normalization | MinMax normalization | Yeo-Johnson normalization |
|---|---|---|
 |
.png "MinMax normalization") |
.png "Yeo-Johnson normalization"){kind=spacer} |
