Figures

CEBRA was introduced in Schneider, Lee and Mathis (2023) and applied to various datasets across animals and recording modalities.

In this section, we provide reference code for reproducing the figures and experiments. Since especially experiments containing parameter sweeps take prohibitely long on a single machine, experiments are grouped in two categories:

• A set of demo notebooks for outlining the most common use cases of CEBRA. These notebooks can be run on a local or hosted jupyter notebook server, or be run in Google colab. To get started with using CEBRA on a set of worked examples, this is the place to start.

• The collection of plotting code for all paper figures. The figures are generated from cached experimental results. For data (re-) analysis and performance comparisons of CEBRA, this is the easiest way to get started.

• The collection of experiments for obtaining results for the figures. Experiments should ideally be run on a GPU cluster with SLURM pre-installed for the best user experience. Alternatively, experiments can also be manually scheduled (our submission system produces a stack of bash files which can be executed on any machine). We recommend this route for follow-up research, when CEBRA (or any of our baselines) should be used for comparisons against other methods.

List of paper figures

We provide reference code for plotting all paper figures here. Note that for the paper version, panels might have been post edited, and the figures might differ in minor typographic details.

List of figures

• Figure 1
• Figure 2
• Figure 3
• Figure 4
• Figure 5
• Extended Data Fig. 1
• Extended Data Fig. 2
• Extended Data Fig. 3
• Extended Data Fig. 4
• Extended Data Fig. 5
• Extended Data Fig. 6
• Extended Data Fig. 7
• Extended Data Fig. 8
• Extended Data Fig. 9
• Extended Data Fig. 10
• Supplementary Table S1 and S2
• Supplementary Table S3 and S4
• Supplementary Table 5
• Supplementary Table 6