cba76ef96c4cd625631ab4d33285b045-Paper-Conference.pdf

Neural Information Processing Systems 

Learning disentangled and distributed representation ofgenerativefactors oftheworld isbelieved tobenefit compositional generalization, because those invariant features canbereused assymbols to build exponentially larger amounts of objects with higher complexity [1, 2, 3, 4].

Similar Docs  Excel Report  more

TitleSimilaritySource
None found