Counting with neurons: rule application with nets of fatiguing leaking integrate and fire neurons.

This paper shows a system that performs simple symbolic processing. The system is based entirely on fatiguing Leaky Integrate and Fire Neurons, a coarse model of neurons. following Hebb, the symbols are encoded by neirons that form Cell Assemblies. Additionally simple rules of the form i f X - X + 1 are encoded by Cell Assemblies, and this symbolic computation is performed. Finally, a more comples rule while X < F - X = X + 1 is encoded using variable binding via a compensatory learning rule. This rule performs the symbolic computation of counting entirely subsymbolically. the binding can be erased and reused via spontaneious neural activation. Unlike the symbolic parallel, the counting rule fails at times when humans might fail