The Concept of Forward-Forward Learning Applied to a Multi Output Perceptron
This is an incremental improvement for simplifying neural network training in classification tasks.
The paper applied the Forward-Forward learning algorithm to a multi-output perceptron for classification, achieving performance comparable to more complex neural networks on datasets with non-linear decision boundaries.
The concept of a recently proposed Forward-Forward learning algorithm for fully connected artificial neural networks is applied to a single multi output perceptron for classification. The parameters of the system are trained with respect to increased (decreased) "goodness" for correctly (incorrectly) labelled input samples. Basic numerical tests demonstrate that the trained perceptron effectively deals with data sets that have non-linear decision boundaries. Moreover, the overall performance is comparable to more complex neural networks with hidden layers. The benefit of the approach presented here is that it only involves a single matrix multiplication.