Reverse engineering recurrent network models reveals mechanisms for location memory
Ian Hawes, Matthew Nolan · FENS Forum 2024
What circuit mechanisms underlie the encoding and retrieval of spatial memory?In standard models, neurons have discrete fields that map onto locations, which are associated with actions. It is unclear if this feedforward mechanism is the only way in which spatial memories can be stored. Here, by reverse-engineering trained recurrent neural networks (RNNs) we identify alternative mechanisms for storage of location memories.We train RNNs on a spatial navigation task where an agent has to navigate to a hidden goal location. Reverse engineering these networks reveals their activity is similar to t
ePoster · Neuroscience