Variable binding by synaptic strength change

Variable binding is a difficult problem for neural networks. Two new mechanisms for binding by synaptic change are presented. The first is based on a common learning mechanism of permanent change of synaptic weight, and the second on synaptic change which decays. Both are biologically motivated. Simulations of binding on a paired association task are shown with the first mechanism succeeding with a 97.5 % F-Score, and the second performing perfectly. Bindings are erased and can be reused. A third simulation of a natural language parser implemented in neurons shows that the mechanisms can be com-bined to take advantage of the speed and capacity characteristics of each. Another common binding mechanism, synchrony, is compatible with these new mechanisms. All three mechanisms are compared and integrated with the Cell Assembly theory.