Predicting Parameters of Adaptive Integrate-and-Fire Models through Machine Learning with Gramian Angular Fields

Abstract: In the field of neuroscience, simulation of neurons and neuronal networks are often of great interest. Before neuron models can be used they require tuning of several parameters to properly replicate characteristics of a given neuron type. There are several methods to do this tuning of parameters but they have one common issue, they are computationally expensive. In an effort to reduce the computational cost we propose in this study the application of Convolutional Neural Networks with Gramian Angular Fields of voltage trace data to the task of parameter optimization through regression. Training and evaluating the network on simulated data from the AdEx model in NEST we found that Convolutional Neural Networks in conjunction with Gramian Angular Fields work exceptionally well on synthetic data; being able to predict all but one parameter with almost all reproduced traces within acceptable error ranges. The method shows great promise. However, this study was based purely on synthetic data. Future work on experimental data is therefore necessary to examine the method’s full capability.