Skip to content
@mackelab

mackelab

Machine Learning in Science at University of Tübingen, Germany

Machine Learning in Science

Our goal is to accelerate scientific discovery using machine learning and artificial intelligence: We develop computational methods that help scientists interpret empirical data and use them to gain scientific insights.

We closely collaborate with experimental researchers from various disciplines. We are particularly interested in applications in the neurosciences: We build data-driven mechanistic models of neuronal functions in order to understand how neuronal networks in the brain process sensory information and control intelligent behaviour.

We are part of the Excellence Cluster Machine Learning Tübingen and the Tübingen AI Center. You can find out more about us on our lab website.

In addition to the repositories in this organization, (former) lab members have also developed the following toolboxes:

  • sbi, a toolbox for simulation-based inference,
  • DECODE, a deep learning tool for single molecule localization microscopy,
  • sbibm, a benchmark for simulation-based inference,
  • flyvis, a connectome constrained deep mechanistic network (DMN) model,
  • Jaxley, a differentiable simulator for biophysical neuron models.

Pinned Loading

  1. mnle-for-ddms mnle-for-ddms Public

    Research code for Mixed Neural Likelihood Estimation (MNLE, Boelts et al. 2022)

    Jupyter Notebook 17 6

  2. phase-limit-cycle-RNNs phase-limit-cycle-RNNs Public

    Code for "Trained recurrent neural networks develop phase-locked limit cycles in a working memory task" - Matthijs Pals (@matthijspals) , Jakob Macke and Omri Barak.

    Python 5 3

  3. neural_timeseries_diffusion neural_timeseries_diffusion Public

    This repository contains research code for the paper "Generating realistic neurophysiological time series with denoising diffusion probabilistic models".

    Python 65 6

  4. sbi-ice sbi-ice Public

    Simulation-Based Inference of Surface Accumulation and Basal Melt Rates of an Antarctic Ice Shelf from Isochronal Layers

    Python 1

  5. STG_energy STG_energy Public

    Repo for STG energy paper. Michael (@michaeldeistler) and Pedro (@ppjgoncalves).

    Jupyter Notebook 1

  6. labproject labproject Public

    Labproject about comparing distributions metrics by @mackelab

    Python 3

Repositories

Showing 10 of 82 repositories
  • sourcerer-sequential Public Forked from mackelab/sourcerer

    A sequential variant of the "Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation" algorithm @swag2198

    mackelab/sourcerer-sequential’s past year of commit activity
    Jupyter Notebook 1 MIT 3 0 0 Updated Nov 27, 2024
  • sequence_memory_NN Public

    Main Figure code and data accompanying paper

    mackelab/sequence_memory_NN’s past year of commit activity
    MATLAB 0 0 0 0 Updated Nov 26, 2024
  • jaxley_experiments Public

    Repository to reproduce results of `Differentiable simulation enables large-scale training of biophysical models of neural dynamics`.

    mackelab/jaxley_experiments’s past year of commit activity
    Jupyter Notebook 1 MIT 1 1 0 Updated Nov 25, 2024
  • LDNS Public
    mackelab/LDNS’s past year of commit activity
    Jupyter Notebook 3 MIT 1 1 0 Updated Nov 25, 2024
  • automind Public

    Automated Model Inference from Neural Dynamics

    mackelab/automind’s past year of commit activity
    Jupyter Notebook 5 Apache-2.0 1 0 0 Updated Nov 22, 2024
  • neuralgbi_diffusion Public Forked from mackelab/neuralgbi

    Richard @rdgao & Michael @michaeldeistler: using neural network-based regression and density estimation for Generalized Bayesian Inference

    mackelab/neuralgbi_diffusion’s past year of commit activity
    Jupyter Notebook 1 MIT 1 0 0 Updated Nov 22, 2024
  • smc_rnns Public

    Code accompanying Inferring stochastic low-rank RNNs from neural data. @Matthijspals

    mackelab/smc_rnns’s past year of commit activity
    Jupyter Notebook 13 Apache-2.0 2 0 0 Updated Nov 8, 2024
  • markovsbi Public

    Public repository for paper: Compositional simulation-based inference for time series.

    mackelab/markovsbi’s past year of commit activity
    2 0 0 0 Updated Oct 28, 2024
  • sequence-memory Public

    Code for Liebe et al. "Phase of firing does not reflect temporal order in sequence memory of humans and recurrent neural networks", code by Matthijs Pals (@Matthijspals)

    mackelab/sequence-memory’s past year of commit activity
    Jupyter Notebook 3 MIT 1 0 0 Updated Oct 7, 2024
  • epiphyte Public

    Python toolkit for working with high-dimensional neural data recorded during naturalistic, continuous stimuli @a-darcher @rachrapp

    mackelab/epiphyte’s past year of commit activity
    Jupyter Notebook 8 GPL-3.0 1 0 0 Updated Sep 13, 2024

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…