Efficient neural decoding of self-location with a deep recurrent network

Autor: H. Freyja Ólafsdóttir, Raul Vicente, Ardi Tampuu, Caswell Barry, Tambet Matiisen
Jazyk: angličtina
Rok vydání: 2019
Předmět:
Male
Computer science
Physiology
Place cell
Hippocampus
Action Potentials
Social Sciences
Hippocampal formation
Machine Learning
0302 clinical medicine
Cognition
Learning and Memory
Mathematical and Statistical Techniques
Animal Cells
Medicine and Health Sciences
Psychology
lcsh:QH301-705.5
Recurrent Neural Networks
Neurons
0303 health sciences
education.field_of_study
Animal Behavior
Applied Mathematics
Simulation and Modeling
Electrophysiology
Place Cells
Physical Sciences
Cellular Types
Neural coding
Algorithms
Neural decoding
Research Article
Computer and Information Sciences
Neural Networks
Population
Models
Neurological
Bayesian Method
Neurophysiology
Bayesian inference
Research and Analysis Methods
Membrane Potential
03 medical and health sciences
Machine Learning Algorithms
Spatial Processing
Memory
Artificial Intelligence
Biological neural network
Animals
education
030304 developmental biology
Behavior
business.industry
Biology and Life Sciences
Pattern recognition
Bayes Theorem
Rats
Inbred Strains
Cell Biology
Rats
Recurrent neural network
lcsh:Biology (General)
Cellular Neuroscience
Cognitive Science
Artificial intelligence
Neural Networks
Computer
business
Zoology
030217 neurology & neurosurgery
Mathematics
Forecasting
Neuroscience
Zdroj: PLoS Computational Biology, Vol 15, Iss 2, p e1006822 (2019)
PLoS Computational Biology
ISSN: 1553-7358
Popis: Place cells in the mammalian hippocampus signal self-location with sparse spatially stable firing fields. Based on observation of place cell activity it is possible to accurately decode an animal’s location. The precision of this decoding sets a lower bound for the amount of information that the hippocampal population conveys about the location of the animal. In this work we use a novel recurrent neural network (RNN) decoder to infer the location of freely moving rats from single unit hippocampal recordings. RNNs are biologically plausible models of neural circuits that learn to incorporate relevant temporal context without the need to make complicated assumptions about the use of prior information to predict the current state. When decoding animal position from spike counts in 1D and 2D-environments, we show that the RNN consistently outperforms a standard Bayesian approach with either flat priors or with memory. In addition, we also conducted a set of sensitivity analysis on the RNN decoder to determine which neurons and sections of firing fields were the most influential. We found that the application of RNNs to neural data allowed flexible integration of temporal context, yielding improved accuracy relative to the more commonly used Bayesian approaches and opens new avenues for exploration of the neural code.
Author summary Being able to accurately self-localize is critical for most motile organisms. In mammals, place cells in the hippocampus appear to be a central component of the brain network responsible for this ability. In this work we recorded the activity of a population of hippocampal neurons from freely moving rodents and carried out neural decoding to determine the animals’ locations. We found that a machine learning approach using recurrent neural networks (RNNs) allowed us to predict the rodents’ true positions more accurately than a standard Bayesian method with flat priors (i.e. maximum likelihood estimator, MLE) as well as a Bayesian approach with memory (i.e. with priors informed by past activity). The RNNs are able to take into account past neural activity without making assumptions about the statistics of neuronal firing. Further, by analyzing the representations learned by the network we were able to determine which neurons, and which aspects of their activity, contributed most strongly to the accurate decoding.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje