no code implementations • 8 May 2024 • Hanqi Zhou, David G. Nagy, Charley M. Wu
Many aspects of human learning have been proposed as a process of constructing mental programs: from acquiring symbolic number representations to intuitive theories about the world.
1 code implementation • 22 Mar 2022 • Timo Flesch, David G. Nagy, Andrew Saxe, Christopher Summerfield
Here, we propose novel computational constraints for artificial neural networks, inspired by earlier work on gating in the primate prefrontal cortex, that capture the cost of interleaved training and allow the network to learn two tasks in sequence without forgetting.
no code implementations • 4 Dec 2017 • David G. Nagy, Gergő Orbán
Alternatively, maintaining only a limited set of models in memory could limit memory requirements.