Deep Networks: Overview

From Ufldl

Jump to: navigation, search
(Advantages of deep networks)
(Advantages of deep networks)
Line 35: Line 35:
the network can compute either the logical OR of its inputs (or the OR of the  
the network can compute either the logical OR of its inputs (or the OR of the  
negation of the inputs), or compute the logical AND.  If we have a network with
negation of the inputs), or compute the logical AND.  If we have a network with
-
only 1 hidden layer, the parity function would require a number of nodes that
+
only one input, one hidden, and one output layer, the parity function would require a number of nodes that
is exponential in the input size <math>n</math>.  If however we are allowed a
is exponential in the input size <math>n</math>.  If however we are allowed a
deeper network, then the network/circuit size can be only polynomial in
deeper network, then the network/circuit size can be only polynomial in

Revision as of 20:22, 13 May 2011

Personal tools