Fig. 3

Learning towards multiple goals. a–d Categorical accuracy against the goal when learning different numbers of goals. Blue indicates the MVG. Black connects the epochs involved in learning Airplane in the MVG. Red indicates the FG of Airplane. The set of goals used for learning is shown in the text. e, f Categorical accuracy against unlearned goals Cat and Ship. The weights of the initial neural network are from the first time it learns Airplane after 600 epochs. g Modularity of the obtained neural network. The neural network is the initial neural network of e, f. h, i 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 (e, f) 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