Part of Advances in Neural Information Processing Systems 3 (NIPS 1990)
Eric Baum, Kevin Lang
While the network loading problem for 2-layer threshold nets is NP-hard when learning from examples alone (as with backpropaga(cid:173) tion), (Baum, 91) has now proved that a learner can employ queries to evade the hidden unit credit assignment problem and PAC-load nets with up to four hidden units in polynomial time. Empirical tests show that the method can also learn far more complicated functions such as randomly generated networks with 200 hidden units. The algorithm easily approximates Wieland's 2-spirals func(cid:173) tion using a single layer of 50 hidden units, and requires only 30 minutes of CPU time to learn 200-bit parity to 99.7% accuracy.