Jakob Macke

Dr. Jakob Macke


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 August 2020 in Journal of Open Source Software
Verified
Journal Article
Open access
PDF file
ATAlvaro Tejero-Cantero
Alvaro Tejero-Cantero
JBJan Boelts
Jan Boelts
MDMichael Deistler
Michael Deistler
JLJan-Matthis Lueckmann
Jan-Matthis Lueckmann
CDConor Durkan
Conor Durkan
JMJakob Macke
Jakob Macke

8 December 2021 in Physical Review Letters
Verified
Journal Article
Open access
PDF file
MDMaximilian Dax
Maximilian Dax
SGStephen R. Green
Stephen R. Green
JGJonathan Gair
Jonathan Gair
JMJakob Macke
Jakob Macke
ABAlessandra Buonanno
Alessandra Buonanno
BSBernhard Schölkopf
Bernhard Schölkopf
We demonstrate unprecedented accuracy for rapid gravitational wave parameter estimation with deep learning. Using neural networks as surrogates for Bayesian posterior distributions, we analyze eight gravitational wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog and find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to 20 s per event. Our networks are trained using simulated data, including an estimate of the detector noise characteristics near the event. This encodes the signal and noise models within millions of neural-network parameters and enables inference for any observed data consistent with the training distribution, accounting for noise nonstationarity from event to event. Our algorithm—called “DINGO”—sets a new standard in fast and accurate inference of physical parameters of detected gravitational wave events, which should enable real-time data analysis without sacrificing accuracy.

17 September 2020 in eLife
Verified
Journal Article
Open access
PGPedro J Gonçalves
Pedro J Gonçalves
JLJan-Matthis Lueckmann
Jan-Matthis Lueckmann
MDMichael Deistler
Michael Deistler
MNMarcel Nonnenmacher
Marcel Nonnenmacher
KÖKaan Öcal
Kaan Öcal
JMJakob Macke
Jakob Macke
Mechanistic modeling in neuroscience aims to explain observed phenomena in terms of underlying causes. However, determining which model parameters agree with complex and stochastic neural data presents a significant challenge. We address this challenge with a machine learning tool which uses deep neural density estimators—trained using model simulations—to carry out Bayesian inference and retrieve the full space of parameters compatible with raw data or selected data features. Our method is scalable in parameters and data features and can rapidly analyze new data after initial training. We demonstrate the power and flexibility of our approach on receptive fields, ion channels, and Hodgkin–Huxley models. We also characterize the space of circuit configurations giving rise to rhythmic activity in the crustacean stomatogastric ganglion, and use these results to derive hypotheses for underlying compensation mechanisms. Our approach will help close the gap between data-driven and theory-driven models of neural dynamics.

3 September 2021 in Nature Methods
Verified
Journal Article
Closed access
PDF file
ASArtur Speiser
Artur Speiser
LMLucas-Raphael Müller
Lucas-Raphael Müller
PHPhilipp Hoess
Philipp Hoess
UMUlf Matti
Ulf Matti
COChristopher J. Obara
Christopher J. Obara
STSrinivas C. Turaga
Srinivas C. Turaga

26 April 2023 in Physical Review Letters
Verified
Journal Article
Open access
PDF file
MDMaximilian Dax
Maximilian Dax
SGStephen R. Green
Stephen R. Green
JGJonathan Gair
Jonathan Gair
MPMichael Pürrer
Michael Pürrer
JWJonas Wildberger
Jonas Wildberger
BSBernhard Schölkopf
Bernhard Schölkopf
We combine amortized neural posterior estimation with importance sampling for fast and accurate gravitational-wave inference. We first generate a rapid proposal for the Bayesian posterior using neural networks, and then attach importance weights based on the underlying likelihood and prior. This provides (1) a corrected posterior free from network inaccuracies, (2) a performance diagnostic (the sample efficiency) for assessing the proposal and identifying failure cases, and (3) an unbiased estimate of the Bayesian evidence. By establishing this independent verification and correction mechanism we address some of the most frequent criticisms against deep learning for scientific inference. We carry out a large study analyzing 42 binary black hole mergers observed by LIGO and Virgo with the SEOBNRv4PHM and IMRPhenomXPHM waveform models. This shows a median sample efficiency of ≈10% (2 orders of magnitude better than standard samplers) as well as a tenfold reduction in the statistical uncertainty in the log evidence. Given these advantages, we expect a significant impact on gravitational-wave inference, and for this approach to serve as a paradigm for harnessing deep learning methods in scientific applications.

21 May 2018 in PLOS Computational Biology
Verified
Journal Article
Open access
PDF file
PBPhilipp Berens
Philipp Berens
JFJeremy Freeman
Jeremy Freeman
TDThomas Deneux
Thomas Deneux
NCNikolay Chenkov
Nikolay Chenkov
TMThomas McColgan
Thomas McColgan
MBMatthias Bethge
Matthias Bethge
In recent years, two-photon calcium imaging has become a standard tool to probe the function of neural circuits and to study computations in neuronal populations. However, the acquired signal is only an indirect measurement of neural activity due to the comparatively slow dynamics of fluorescent calcium indicators. Different algorithms for estimating spike rates from noisy calcium measurements have been proposed in the past, but it is an open question how far performance can be improved. Here, we report the results of the spikefinder challenge, launched to catalyze the development of new spike rate inference algorithms through crowd-sourcing. We present ten of the submitted algorithms which show improved performance compared to previously evaluated methods. Interestingly, the top-performing algorithms are based on a wide range of principles from deep neural networks to generative models, yet provide highly correlated estimates of the neural activity. The competition shows that benchmark challenges can drive algorithmic developments in neuroscience. Two-photon calcium imaging is one of the major tools to study the activity of large populations of neurons in the brain. In this technique, a fluorescent calcium indicator changes its brightness when a neuron fires an action potential due to an associated increase in intracellular calcium. However, while a number of algorithms have been proposed for estimating spike rates from the measured signal, the problem is far from solved. We organized a public competition using a data set for which ground truth data was available. Participants were given a training set to develop new algorithms, and the performance of the algorithms was evaluated on a hidden test set. Here we report on the results of this competition and discuss the progress made towards better algorithms to infer spiking activity from imaging data.