[Paper Review] Understanding and Controlling Memory in Recurrent Neural Networks
[Paper Review] A complexity-based theory of compositionality
[Paper Review] The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation
[Paper Review] Flexible multitask computation in recurrent networks utilizes shared dynamical motifs
[Paper Review] Task representations in neural networks trained to perform many cognitive tasks