|
NeuroCOLT |
Neural Networks and Computational Learning Theory |
||||||||
|
|
NeuroCOLT Technical Report NC-TR-01-114
ABSTRACT We introduce total {\em wire length} as salient complexity measure for analyzing the circuit complexity of sensory processing in biological neural systems and neuromorphic engineering. The new complexity measure is applied in this paper to two basic computational problems that arise in translation- and scale-invariant pattern recognition, and hence appear to be useful as benchmark problems for sensory processing. We exhibit new circuit design strategies for these benchmark functions that can be implemented within realistic complexity bounds, in particular with linear or almost linear total wire length. In addition we derive general bounds for the total wire length of circuits in terms of traditional complexity measures.
|