A faster way to model neuronal circuitry

Article Mathematical & Computational Biology

Predicting Spike Features of Hodgkin-Huxley-Type Neurons With Simple Artificial Neural Network

Tian Wang et al.

Summary: This study proposed a feature prediction module based on a simple artificial neural network to predict specific features of neuronal spikes. Experimental results demonstrated that the combination of the feature prediction module and the spike prediction module accurately predicts the spiking behavior of different types of HH-type models and can generalize to unseen types of input current. The integration of the two modules offers a potential way to simulate the action potentials of biological neurons with high accuracy and efficiency.

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE (2022)

Add to Collection

Article Biology

Ultrafast simulation of large-scale neocortical microcircuitry with biophysically realistic neurons

Viktor J. Olah et al.

Summary: Understanding the activity of the mammalian brain requires a comprehensive understanding of circuits at different scales, and computational models can help us understand how various parameters synergistically contribute to circuit behavior. However, traditional neuron models are computationally demanding, so we propose a training artificial neural network approach to simulate realistic neural activity. We found that the artificial neural network accurately predicts subthreshold activity and action potential firing, and can generalize to previously unobserved synaptic inputs, with processing times orders of magnitude faster than traditional methods.

ELIFE (2022)

Add to Collection

Editorial Material Multidisciplinary Sciences

Opportunities and challenges for machine learning in weather and climate modelling: hard, medium and soft AI

Matthew Chantry et al.

Summary: The workshop in September 2019 highlighted the growing area of applying machine learning to improve weather and climate prediction, outlining motivations, opportunities, and challenges ahead. This article is part of the theme issue on 'Machine learning for weather and climate modelling'.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2021)

Add to Collection

Article Neurosciences

Single cortical neurons as deep artificial neural networks

David Beniaguev et al.

Summary: Through machine learning, a systematic approach to characterize neurons' input/output mapping complexity has been introduced, highlighting the use of deep neural networks for capturing complex I/O mapping in realistic models of cortical neurons. The study also reveals that synaptic integration in dendritic branches can be conceptualized as pattern matching from a set of spatiotemporal templates, shedding light on the computational complexity of single neurons and the unique architecture of cortical networks.

NEURON (2021)

Add to Collection

Article Economics

Recurrent Neural Networks for Time Series Forecasting: Current status and future directions

Hansika Hewamalage et al.

Summary: Although Recurrent Neural Networks (RNNs) have shown competitive forecasting performance, they are not always superior to established statistical models such as exponential smoothing (ETS) and autoregressive integrated moving average (ARIMA).

INTERNATIONAL JOURNAL OF FORECASTING (2021)

Add to Collection

Article Neurosciences