Abstract: In this paper, a self-developing neural network model, namely the Growing Cell Structures
(GCS) is characterized. In GCS each node (or cell) is associated with a local resource counter τ (t ).
We show that GCS has the conservation property by which the summation of all resource counters
always equals s(1−α)
α , thereby s is the increment added to τ (t ) of the wining node after each input
presentation and α(0 <α< 1.0) is the forgetting (i.e., decay) factor applied to τ (t ) of non-wining
nodes. The conservation property provides an insight into how GCS can maximize information
entropy. The property is also employed to unveil the chain-reaction effect and race-condition which
can greatly influence the performance of GCS. We show that GCS can perform better in terms of
equi-probable criterion if the resource counters are decayed by a smaller α.