Our paper is out in @natmachintell.nature.com!
We trained multiple RNNs to perform free recall. The best-performing ones learned a strategy akin to the memory palace technique. See thread below for more info.
www.nature.com/articles/s42...
nature.com
A neural network model of free recall learns multiple memory strategies - Nature Machine Intelligence
Li et al. show that recurrent neural networks optimized for free recall discover diverse, human-like memory strategies beyond classical temporal context models, with top models using an index-based me...