PsychologyNature
Discovering cognitive strategies with tiny recurrent neural networks
L. Ji-an, M. K. Benna, et al.
We introduce a novel modelling approach using recurrent neural networks to discover cognitive algorithms underlying biological decision-making. Small networks (1–4 units) often outperform classical models, match larger nets, and—interpretable via dynamical-systems analysis—reveal mechanisms and behavioural dimensionality. Research conducted by Li Ji-An, Marcus K. Benna, and Marcelo G. Mattar.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Psychology
Neural representational geometries reflect behavioral differences in monkeys and recurrent neural networks
V. Fascianelli, A. Battista, et al.
Computer Science
Comparing feedforward and recurrent neural network architectures with human behavior in artificial grammar learning
A. Alamia, V. Gauducheau, et al.
Physics
Efficient quantum state tomography with convolutional neural networks
T. Schmale, M. Reh, et al.
Physics
Adaptive quantum state tomography with neural networks
Y. Quek, S. Fort, et al.
