Pile vs Neural Networks

Data, e.g. "PETER", are not held "in the system" themselves, but are represented by "placeholders" or the linking of "placeholders". The data itself is therefore not "in the system", but can only be generated from it again.

Pile is bidirectional in this respect and thus contrasts with e.g. neural networks, which also encode data/signals but do not reliably re-produce them. However, that is not their purpose. But that is the purpose of a pile – and insofar it is and remains a data storage. (Ralf Westphal (2006), personal communication)

~