Anna Levina — accepted AI-conference papers

2024

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

Sina Khajehabdollahi, Roxana Zeraati, Emmanouil Giannakakis, Tim Jakob Schäfer, Georg Martius, Anna Levina

ICLR 2024poster

Recurrent neural networks (RNNs) in the brain and \emph{in silico} excel at solving tasks with intricate temporal dependencies. Long timescales required for solving such tasks can arise from properties of individual neurons (single-neuron timescale, $\tau$, e.g., membrane time constant in biological…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2024

Learning with 3D rotations, a hitchhiker's guide to SO(3)

Andreas René Geist, Jonas Frey, Mikel Zhobro, Anna Levina, Georg Martius

ICML 2024poster

Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. This paper acts as a survey and guide through rotation representations. We walk through their properties that harm or bene…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2024

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.

Aaron Spieler, Nasim Rahaman, Georg Martius, Bernhard Schölkopf, Anna Levina

ICLR 2024poster

Biological cortical neurons are remarkably sophisticated computational devices, temporally integrating their vast synaptic input over an intricate dendritic tree, subject to complex, nonlinearly interacting internal biological processes. A recent study proposed to characterize this complexity by fi…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗