• Corpus ID: 12669085

Fast amortized inference of neural activity from calcium imaging data with variational autoencoders

@article{Speiser2017FastAI,
  title={Fast amortized inference of neural activity from calcium imaging data with variational autoencoders},
  author={Artur Speiser and Jinyao Yan and Evan Archer and Lars Buesing and Srinivas C. Turaga and Jakob H. Macke},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.01846}
}
Calcium imaging permits optical measurement of neural activity. [] Key Method The recognition network is trained to produce samples from the posterior distribution over spike trains. Once trained, performing inference amounts to a fast single forward pass through the network, without the need for iterative optimization or sampling.

Figures and Tables from this paper

Community-based benchmarking improves spike rate inference from two-photon calcium imaging data

The results of the spikefinder challenge, launched to catalyze the development of new spike rate inference algorithms through crowd-sourcing, are reported, and the top-performing algorithms are based on a wide range of principles, yet provide highly correlated estimates of the neural activity.

Community-based benchmarking improves spike inference from two-photon calcium imaging data

The results of the spikefinder challenge, launched to catalyze the development of new spike inference algorithms through crowd-sourcing, are reported, and ten of the submitted algorithms are presented which show improved performance compared to previously evaluated methods.

High frequency spike inference with particle Gibbs sampling

This study introduces an auto-regressive generative model that accounts for bursting neuronal activity and baseline fluorescence modulation, and it also applies recent sequential Monte Carlo approaches to obtain joint posterior distributions of static and dynamic model parameters.

Signal-to-signal neural networks for improved spike estimation from calcium imaging data

A novel neural network-based data-driven algorithm that takes the fluorescence recording as the input and synthesizes the spike information signal, which is well-correlated with the actual spike positions, and outperforms state-of-the-art methods on standard evaluation framework.

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

This work presents a Bayesian modelling approach for localizing the source of individual spikes on high-density, microelectrode arrays and demonstrates that it is more accurate than and can improve spike sorting performance over heuristic localization methods such as center of mass.

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

This work presents a Bayesian modelling approach for localizing the source of individual spikes on high-density, microelectrode arrays and demonstrates that it is more accurate than and can improve spike sorting performance over heuristic localization methods such as center of mass.

Inference of Multiplicative Factors Underlying Neural Variability in Calcium Imaging Data

A flexible modeling framework is developed that identifies low-dimensional latent factors in calcium imaging data with distinct additive and multiplicative modulatory effects that govern trial-to-trial variation in evoked responses and applies it to experimental data from the zebrafish optic tectum.

Parallel inference of hierarchical latent dynamics in two-photon calcium imaging of neuronal populations

The system VaLPACa (Variational Ladders for Parallel Autoencoding of Calcium imaging data) solves the problem of disentangling deeper- and shallower-level dynamics by incorporating a ladder architecture that can infer a hierarchy of dynamical systems by incorporating sequential variational autoencoders.

LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos

This work proposes LeMoNADe, a new exploratory data analysis method that facilitates hunting for motifs in calcium imaging videos, the dominant microscopic functional imaging modality in neurophysiology.

CALFADS: LATENT FACTOR ANALYSIS OF DYNAMI- CAL SYSTEMS IN CALCIUM IMAGING DATA

  • Computer Science
  • 2020
The results demonstrate that variational ladder autoencoders are a promising approach for inferring hierarchical dynamics in experimental settings where the measured variable has its own slow dynamics, such as calcium imaging data.

References

SHOWING 1-10 OF 37 REFERENCES

Fast Active Set Methods for Online Deconvolution of Calcium Imaging Data

This work presents a fast online active set method that enables real-time simultaneous deconvolution of whole-brain larval zebrafish imaging data on a laptop, and is a generalization of the pool adjacent violators algorithm for isotonic regression and inherits its linear-time computational complexity.

Fast nonnegative deconvolution for spike train inference from population calcium imaging.

This work presents a fast nonnegative deconvolution filter to infer the approximately most likely spike train of each neuron, given the fluorescence observations, which outperforms optimal linear deconVolution (Wiener filtering) on both simulated and biological data.

Inferring Neuronal Dynamics from Calcium Imaging Data Using Biophysical Models and Bayesian Inference

This work describes, in a novel Bayesian approach, how principled knowledge about neuronal dynamics can be employed to infer biophysical variables and parameters from fluorescence traces and demonstrates that the new approach is able to reconstruct different repetitive spiking and/or bursting patterns with accurate single spike resolution.

Accurate spike estimation from noisy calcium signals for ultrafast three-dimensional imaging of large neuronal populations in vivo

This work proposes a method, MLspike, which returns the most likely spike train underlying the measured calcium fluorescence, which relies on a physiological model including baseline fluctuations and distinct nonlinearities for synthetic and genetically encoded indicators.

Benchmarking Spike Rate Inference in Population Calcium Imaging

Direct Estimation of Firing Rates from Calcium Imaging Data

This work proposes an alternative analysis that aims to estimate the underlying rate directly, by integrating over the unobserved spikes instead of committing to a single estimate of the spike train, and shows that directly estimated rates are more accurate than those obtained from averaging of spikes estimated through deconvolution.

Bayesian spike inference from calcium imaging data

The Rao-Blackwellized extensions serve as complements to standard point estimates and allow for quantification of uncertainty in estimating the underlying spike train and model parameters.

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and