Episodic memory supports the acquisition of structured task representations
Lu, Q.; Hummos, A.; Norman, K. A.
Show abstract
Generalization to new tasks requires learning of task representations that accurately reflect the similarity structure of the task space. Here, we argue that episodic memory (EM) plays an essential role in this process by stabilizing task representations, thereby supporting the accumulation of structured knowledge. We demonstrate this using a neural network model that infers task representations that minimize the current tasks objective function; crucially, the model can retrieve previously encoded task representations from EM and use these to initialize the task inference process. With EM, the model succeeds in learning the underlying task structure; without EM, task representations drift and the network fails to learn the structure. We further show that EM errors can support structure learning by promoting the activation of similar task representations in tasks with similar sensory inputs. Overall, this model provides a novel account of how EM supports the acquisition of structured task representations.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Recurrent Neural Network Model for Flexible and Adaptive Decision Making based on Sequence Learning 97%
- Artificial neural networks for model identification and parameter estimation in computational cognitive models 95%
- Towards a More General Understanding of the Algorithmic Utility of Recurrent Connections 95%
Similar papers in this journal
- When to retrieve and encode episodic memories: a neural network model of hippocampal-cortical interaction 97%
- Gated recurrence enables simple and accurate sequence prediction in stochastic, changing, and structured environments 97%
- The Recurrent Temporal Restricted Boltzmann Machine Captures Neural Assembly Dynamics in Whole-brain Activity 96%
Similar papers in this journal
- Using top-down modulation to optimally balance shared versus separated task representations 97%
- Learning to segment self-generated from externally caused optic flow through sensorimotor mismatch circuits 94%
- A biologically inspired architecture with switching units can learn to generalize across backgrounds 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.