A study compared a parallel distributed processing (PDP) model with a more traditional symbolic information processing model that accounts for early reading acquisition by human subjects. Two experimental paradigms were simulated. In one paradigm (a "savings" paradigm) subjects were divided into two groups and trained with two sets of stimuli: consistent orthographic representation of voicing, or inconsistent mapping of orthography onto voicing. A total of 32 simulated trials were generated with each model. Analysis of the savings paradigm data for the symbolic model revealed no significant main or interaction effects. Analysis of the PDP data revealed significant main and interaction effects. A second paradigm involved a forced-choice task testing subjects' ability to make use of analytic generalization. A total of eight simulated trials were generated with each model. Analysis indicated no significant difference between the symbolic model and chance performance, while the PDP model had perfect performance, indicating that the network had learned to make use of the orthography-voicing relationship implicit in the stimuli. Findings suggest that, in the domain of early reading acquisition, the problem with the PDP model approach is not that it is too weak but that it is too strong--even the simplest PDP models exhibit learning beyond what is observed in human subjects faced with similar learning tasks. (Contains 18 references. An appendix of data is attached.) (RS)