Learning statistical neutral tasks without expert guidance

In this paper, we question the necessity of levels of expert-guided abstraction in learning hard, statistically neutral classification tasks. We focus on two tasks, date calculation and parity-12, that are claimed to require intermediate levels of abstraction that must be defined by a human expert. We challenge this claim by demonstrating empirically that a single hidden-layer BP-SOM network can learn both tasks without guidance. Moreover, we analyze the network's solution for the parity-12 task and show that its solution makes use of an elegant intermediary checksum computation.