rstb20190637_si_001.pdf (635.62 kB)

Supplementary Materials Sections 1 and 2 from Integration of new information in memory: new insights from a complementary learning systems perspective

Download (635.62 kB)
journal contribution
posted on 17.03.2020, 13:32 by James L. McClelland, Bruce L. McNaughton, Andrew K. Lampinen
Provides theoretical and empirical investigations of the process of learning adjustments to known dimensions of knowledge in deep linear networks, and presents results on the dynamics of learning a new item in a pretrained linear autoassociative network.