Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Lightweight Architecture for Real-Time Neuronal-Spike Classification

Muhammad Ali Siddiqi, David Vrijenhoek, Lennart P. L. Landsmeer, Job van der Kleij, Anteneh Gebregiorgis, Vincenzo Romano, Rajendra Bishnoi, Said Hamdioui, Christos Strydis

TL;DR

The paper tackles the challenge of wire-free, long-duration cerebellar recordings by moving real-time spike detection and Purkinje-cell spike classification onto a lightweight, on-head-stage system. It combines a dynamic-threshold spike detector, an 8-bit quantized multilayer perceptron classifier, and STT-RAM storage to condense neural data into spike-event labels stored locally. Key contributions include a four-layer NN topology (16/7/5/4), end-to-end hardware/software flow, offline post-processing for false detections, and demonstrated operation within a 26 mm^2 area with battery life up to several days. This enables naturalistic, freely moving mouse experiments and can significantly improve understanding of cerebellar motor control and injury mechanisms by collecting long, untethered neural data.

Abstract

Electrophysiological recordings of neural activity in a mouse's brain are very popular among neuroscientists for understanding brain function. One particular area of interest is acquiring recordings from the Purkinje cells in the cerebellum in order to understand brain injuries and the loss of motor functions. However, current setups for such experiments do not allow the mouse to move freely and, thus, do not capture its natural behaviour since they have a wired connection between the animal's head stage and an acquisition device. In this work, we propose a lightweight neuronal-spike detection and classification architecture that leverages on the unique characteristics of the Purkinje cells to discard unneeded information from the sparse neural data in real time. This allows the (condensed) data to be easily stored on a removable storage device on the head stage, alleviating the need for wires. Synthesis results reveal a >95% overall classification accuracy while still resulting in a small-form-factor design, which allows for the free movement of mice during experiments. Moreover, the power-efficient nature of the design and the usage of STT-RAM (Spin Transfer Torque Magnetic Random Access Memory) as the removable storage allows the head stage to easily operate on a tiny battery for up to approximately 4 days.

A Lightweight Architecture for Real-Time Neuronal-Spike Classification

TL;DR

The paper tackles the challenge of wire-free, long-duration cerebellar recordings by moving real-time spike detection and Purkinje-cell spike classification onto a lightweight, on-head-stage system. It combines a dynamic-threshold spike detector, an 8-bit quantized multilayer perceptron classifier, and STT-RAM storage to condense neural data into spike-event labels stored locally. Key contributions include a four-layer NN topology (16/7/5/4), end-to-end hardware/software flow, offline post-processing for false detections, and demonstrated operation within a 26 mm^2 area with battery life up to several days. This enables naturalistic, freely moving mouse experiments and can significantly improve understanding of cerebellar motor control and injury mechanisms by collecting long, untethered neural data.

Abstract

Electrophysiological recordings of neural activity in a mouse's brain are very popular among neuroscientists for understanding brain function. One particular area of interest is acquiring recordings from the Purkinje cells in the cerebellum in order to understand brain injuries and the loss of motor functions. However, current setups for such experiments do not allow the mouse to move freely and, thus, do not capture its natural behaviour since they have a wired connection between the animal's head stage and an acquisition device. In this work, we propose a lightweight neuronal-spike detection and classification architecture that leverages on the unique characteristics of the Purkinje cells to discard unneeded information from the sparse neural data in real time. This allows the (condensed) data to be easily stored on a removable storage device on the head stage, alleviating the need for wires. Synthesis results reveal a >95% overall classification accuracy while still resulting in a small-form-factor design, which allows for the free movement of mice during experiments. Moreover, the power-efficient nature of the design and the usage of STT-RAM (Spin Transfer Torque Magnetic Random Access Memory) as the removable storage allows the head stage to easily operate on a tiny battery for up to approximately 4 days.
Paper Structure (21 sections, 8 figures, 5 tables)

This paper contains 21 sections, 8 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Neuroscientific Background
  4. Related Work
  5. Proposed Solution
  6. Spike Detection
  7. Spike Classification
  8. Choice of NN Topology
  9. Choice of Activation Functions
  10. NN Quantization
  11. Control
  12. Storage
  13. Post-processing
  14. Results
  15. Experimental Setup
  16. ...and 6 more sections

Figures (8)

  • Figure 1: A typical wired neural-signal acquisition setup, which limits the free movement of mice.
  • Figure 2: Current wired setups vs. our approach, which gets rid of the wire and enables free movement of mice.
  • Figure 3: Proposed system architecture.
  • Figure 4: Relative timing information between complex and simple spikes, which can aid in the offline post-processing
  • Figure 5: Employed tool flow
  • ...and 3 more figures