Answers are grounded in this paper and cite their sources.
We obtained an analytical expression for the computational complexity of many layered committee machines with a finite number of hidden layers (L < ∞) using the generalization complexity measure introduced by Franco et al. [1]. Although our result is valid in the large size limit and for an overlap synaptic matrix that is ultrametric, it provides a useful tool for inferring the appropriate architecture a network must have to reproduce an arbitrary realizable Boolean function. PACS numbers: 89.70.Eg, 84.35.+i Submitted to: J. Phys. A: Math. Gen. Computational capabilities of multilayer committee machines 2
No takes yet. Share an insight, caveat, or question.
Neirotti et al. (2010) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: