How to model inhibitory synapses in the artificial neuron? [Biological inspiration]

manpreet Best Answer 2 years ago

In the brain some synapses are stimulating and some inhibiting. ReLu erases that property to only stimulating once, since in the brain inhibition doesn't mean 0 output, but more precisely - negative input.

In the brain positive and negative potential is summed up and if it passed the threshold - the neuron fires.

There are 2 main non-linearities which came to my mind in the biological unit:

• potential change is more exponential than linear: small amount of ion channels is sufficient to start a chain-reaction of other channels activation's - which rapidly change global neuron's potential.
• the threshold of the neuron is also non-linear: neuron fires only when the sum of its positive and negative potentials passed given (positive) threshold

So is there any idea how to implement negative input to the artificial neural network?

I gave examples of non-linearities in biological neuron because the most obvious positive/negative unit is just linear unit. But since it doesn't implement non-linearity - we may consider to implement non-linearities somewhere else in the artificial neuron.

manpreet 2 years ago