Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks

no code implementations • 22 Sep 2023 • Sina Khajehabdollahi, Roxana Zeraati, Emmanouil Giannakakis, Tim Jakob Schäfer, Georg Martius, Anna Levina

We find that for both tasks RNNs develop longer timescales with increasing $N$, but depending on the learning objective, they use different mechanisms.

Topology-dependent coalescence controls scaling exponents in finite networks

no code implementations • 11 Nov 2022 • Roxana Zeraati, Victor Buendía, Tatiana A. Engel, Anna Levina

Here we show that distinct empirical exponents arise in networks with different topology and depend on the network size.

Spatial and temporal correlations in neural networks with structured connectivity

no code implementations • 16 Jul 2022 • Yan-Liang Shi, Roxana Zeraati, Anna Levina, Tatiana A. Engel

We show that the network dynamics and connectivity jointly define the spatiotemporal profile of neural correlations.