Back to search

Georgia Institute of Technology

General and interpretable models for inferring dynamical computation in biological neural networks

Abstract

dc:description.abstract

The sequential autoencoder (SAE) has proven to be a powerful deep architecture for modeling large-scale electrophysiological recordings, with a variety of applications in neuroscience and neural engineering. In particular, latent factor analysis via dynamical systems (LFADS) explicitly models latent dynamics and inputs to infer firing rates with state-of-the-art accuracy. However, effectively fitting such models requires time consuming and resource-intensive hyperparameter tuning with reference to supervisory information (e.g. behavioral data) for each new dataset. Additionally, the conditions under which the dynamics learned by the SAE faithfully reflect those of the underlying biological system are unclear and under-explored, limiting the insights that can be gained from internal components of the model. The objectives of this thesis are to simplify training of deep, dynamics-based neural population models on binned spiking activity and to improve the interpretability of the latent dynamics they learn. The first aim of this research was to develop a framework for robust training of SAEs on neural data. In Chapter 2, we present a novel regularization strategy and an efficient hyperparameter tuning approach which allowed us to reliably obtain high-performing models on a wide variety of datasets. The second aim was to evaluate and improve the interpretability of the latent dynamics learned by SAEs. In Chapter 3, we show that widely-used recurrent neural networks (RNNs) struggle to accurately recover dynamics from synthetic datasets, and that neural ordinary differential equations solve many of these issues. The last aim was to address several of the practical challenges of training and applying SAEs in neuroscience. Finally, we describe two open-source projects: a simple, modular, and extensible implementation of LFADS (Chapter 4) and a deployment framework that makes it easier to leverage managed infrastructure for large-scale training (Chapter 5).

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Biomedical Engineering (Joint GT/Emory Department)
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Sedler, Andrew R.
Advisor dc:contributor.advisor
  • Pandarinath, Chethan
Committee members dc:contributor.committeemember
  • Dyer, Eva L.
  • Choi, Hannah
  • Davenport, Mark A.
  • Brody, Carlos D.

Subjects

dc:subject × 6

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/72102

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Sedler, Andrew R.. General and interpretable models for inferring dynamical computation in biological neural networks. Doctoral thesis, Georgia Institute of Technology, 2023. https://hdl.handle.net/1853/72102