A Priori Estimation of Classification Circuit Complexity

The paper aims at tight upper bounds for the size of pattern classification circuits that can be used for ap rioriparameter settings in a machine learning context. The upper bounds relate the circuit size S(C )t onL := � log2 mL� ,w heremL is the number of training samples. In particular, we show that there exist unbounded fan- in threshold circuits with less than (a) SR cc := 2 · √ 2nL + 3 gates for unbounded