Fig. 4

Learning towards different combinations of goals. a Categorical accuracy against the goal in learning. Blue indicates the MVG of Bird and Dog. Black connects the epochs involved in learning Bird in the MVG. Red indicates the FG of Bird. Purple indicates Rcost. b, c Categorical accuracy against unlearned goals Cat and Ship. The weights of the initial neural network are from the last epoch of (a). e, d Pearson’s correlation coefficient (cc) against before and after learning the unlearned goals Cat and Ship. The cc of the filter elements of the initial neural network and the last neural network in (b, c) is shown. Blue indicates the cc values of all the filter elements. Red indicates the cc values of elements in the filter corresponding to intra-module links. Purple indicates the cc values of elements in the filter corresponding to inter-module links