Biologically Extending the Gen 2 ANN Model

In this paper the generations of artificial neural net- works (ANN) are surveyed. The assumptions present in Gen 1 and 2 ANNs are enumerated. In the pro- cess of reformulating the Gen 2 ANN an extension was observed that could increase the biological plausibility of the model. The resulting model makes use of the neurological interneuron structures that provide inhibi- tion and input gain control in the cortical regions of the brain. The resulting interneuron neural network (INN) is applied to the well know MNIST. The INN beats an identical ANN. The application of the model is used to validate the derivation of the model and associated backpropagation.