Interpretable deep learning for deconvolutional analysis of neural signals.

Journal: Neuron
PMID:

Abstract

The widespread adoption of deep learning to model neural activity often relies on "black-box" approaches that lack an interpretable connection between neural activity and network parameters. Here, we propose using algorithm unrolling, a method for interpretable deep learning, to design the architecture of sparse deconvolutional neural networks and obtain a direct interpretation of network weights in relation to stimulus-driven single-neuron activity through a generative model. We introduce our method, deconvolutional unrolled neural learning (DUNL), and demonstrate its versatility by applying it to deconvolve single-trial local signals across multiple brain areas and recording modalities. We uncover multiplexed salience and reward prediction error signals from midbrain dopamine neurons, perform simultaneous event detection and characterization in somatosensory thalamus recordings, and characterize the heterogeneity of neural responses in the piriform cortex and across striatum during unstructured, naturalistic experiments. Our work leverages advances in interpretable deep learning to provide a mechanistic understanding of neural activity.

Authors

  • Bahareh Tolooshams
    Center for Brain Science, Harvard University, Cambridge, MA 02138, USA; John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA; Computing + mathematical sciences, California Institute of Technology, Pasadena, CA 91125, USA.
  • Sara Matias
    Center for Brain Science, Harvard University, Cambridge, MA 02138, USA; Department of Molecular and Cellular Biology, Harvard University, Cambridge, MA 02138, USA.
  • Hao Wu
    Zhejiang Institute of Tianjin University (Shaoxing), Shaoxing, China.
  • Simona Temereanca
    Carney Institute for Brain Science, Brown University, Providence, RI 02906, USA.
  • Naoshige Uchida
    Harvard University, Cambridge, United States.
  • Venkatesh N Murthy
    Department of Molecular & Cellular Biology and Center for Brain Science, Harvard University, Cambridge, MA, USA.
  • Paul Masset
    Center for Brain Science, Harvard University, Cambridge, MA 02138, USA; Department of Molecular and Cellular Biology, Harvard University, Cambridge, MA 02138, USA; Department of Psychology, McGill University, Montréal, QC H3A 1G1, Canada; Mila - Quebec Artificial Intelligence Institute, Montréal, QC H2S 3H1, Canada. Electronic address: paul.masset@mcgill.ca.
  • Demba Ba
    School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138.