AI RESEARCH
On the Role of Depth in the Expressivity of RNNs
arXiv CS.LG
•
ArXi:2604.02201v1 Announce Type: new The benefits of depth in feedforward neural networks are well known: composing multiple layers of linear transformations with nonlinear activations enables complex computations. While similar effects are expected in recurrent neural networks (RNNs), it remains unclear how depth interacts with recurrence to shape expressive power.