Dictionary learning for spontaneous neural activity modeling

Abstract

Abstract-Modeling the activity of an ensemble of neurons can provide critical insights into the workings of the brain. In this work we examine if learning based signal modeling can contribute to a high quality modeling of neuronal signal data. To that end, we employ the sparse coding and dictionary learning schemes for capturing the behavior of neuronal responses into a small number of representative prototypical signals. Performance is measured by the reconstruction quality of clean and noisy test signals, which serves as an indicator of the generalization and discrimination capabilities of the learned dictionaries. To validate the merits of the proposed approach, a novel dataset of the actual recordings from 183 neurons from the primary visual cortex of a mouse in early postnatal development was developed and investigated. The results demonstrate that high quality modeling of testing data can be achieved from a small number of training examples and that the learned dictionaries exhibit significant specificity when introducing noise.

Adversarial dictionary learning for a robust analysis and modelling of spontaneous neuronal activity

“…where RMSE is the root mean squared error. In case of 6) this means that the example y i , which was only included in D had indeed an effective result in the representation of the validation set V clean . We will keep up with the description of the second stage of our algorithm, which is partially inspired from adversarial learning methods [13,14], justifying the characterism adversarial that we have given to it.…”

“…In brain signaling specifically, the K-SVD algorithm [5], has been used for capturing the behavior of neuronal responses into a dictionary, which was evaluated with realworld data for its generalization capacity as well as for its sensitivity with respect to noise [6]. DL has been also suggested for the EEG (electroencephalography) inverse problem.…”