In the field of neuroscience, analyzing brain signals and identifying relevant patterns pose significant challenges. The brain's complex structure and non-linear nature makes it difficult to classify and detect patterns within raw brain signals.Extracellular electrophysiology recordings capturing the activity of neuronal populations, e.g., Local Field Potentials (LFPs), have offered important insights into cortical dynamics. Yet there is still a lack of clarity about how features and characteristics of these extracellular potentials relate to the properties and function of the underlying neural populations. Mechanistic models combined with simulation-based inference (SBI) algorithms have emerged as an effective strategy for developing predictive tools that fit well with available empirical data and can be used to predict key parameters that describe neural activity. Numerous SBI techniques rely on summary statistics or interpretable features to approximate the likelihood or posterior. However, at present, a significant challenge is assessing how each feature impacts the SBI model's predictions. Here, it was developed an approach to determine feature importance in the context of cortical circuit parameter inference. it was first created a dataset that includes a million distinct simulations from a spiking cortical microcircuit model of recurrently connected excitatory and inhibitory populations. Biophysics-based causal filters were coupled with spikes to generate realistic LFP data. Then, it was extracted a set of meaningful features from simulated LFP data that were used to train an SBI algorithm. To evaluate feature importance, differents tecnichs were used like mutual information (MI), principal component analisis (PCA) and SHAP values, a prominent tool in machine learning for interpreting the contribution of eachfeature to the prediction outcomes. The results demonstrate the effectiveness of this approach in identifying the most critical features for inferring the parameters of a recurrent cortical circuit model based on electrophysiological data. These results were presented at the Brain Informatics 2024 International Conference.
In the field of neuroscience, analyzing brain signals and identifying relevant patterns pose significant challenges. The brain's complex structure and non-linear nature makes it difficult to classify and detect patterns within raw brain signals.Extracellular electrophysiology recordings capturing the activity of neuronal populations, e.g., Local Field Potentials (LFPs), have offered important insights into cortical dynamics. Yet there is still a lack of clarity about how features and characteristics of these extracellular potentials relate to the properties and function of the underlying neural populations. Mechanistic models combined with simulation-based inference (SBI) algorithms have emerged as an effective strategy for developing predictive tools that fit well with available empirical data and can be used to predict key parameters that describe neural activity. Numerous SBI techniques rely on summary statistics or interpretable features to approximate the likelihood or posterior. However, at present, a significant challenge is assessing how each feature impacts the SBI model's predictions. Here, it was developed an approach to determine feature importance in the context of cortical circuit parameter inference. it was first created a dataset that includes a million distinct simulations from a spiking cortical microcircuit model of recurrently connected excitatory and inhibitory populations. Biophysics-based causal filters were coupled with spikes to generate realistic LFP data. Then, it was extracted a set of meaningful features from simulated LFP data that were used to train an SBI algorithm. To evaluate feature importance, differents tecnichs were used like mutual information (MI), principal component analisis (PCA) and SHAP values, a prominent tool in machine learning for interpreting the contribution of eachfeature to the prediction outcomes. The results demonstrate the effectiveness of this approach in identifying the most critical features for inferring the parameters of a recurrent cortical circuit model based on electrophysiological data. These results were presented at the Brain Informatics 2024 International Conference.
Inference of cortical circuit parameters based on simulation of biophysically complex brain models
SANDRON, ALESSANDRO
2023/2024
Abstract
In the field of neuroscience, analyzing brain signals and identifying relevant patterns pose significant challenges. The brain's complex structure and non-linear nature makes it difficult to classify and detect patterns within raw brain signals.Extracellular electrophysiology recordings capturing the activity of neuronal populations, e.g., Local Field Potentials (LFPs), have offered important insights into cortical dynamics. Yet there is still a lack of clarity about how features and characteristics of these extracellular potentials relate to the properties and function of the underlying neural populations. Mechanistic models combined with simulation-based inference (SBI) algorithms have emerged as an effective strategy for developing predictive tools that fit well with available empirical data and can be used to predict key parameters that describe neural activity. Numerous SBI techniques rely on summary statistics or interpretable features to approximate the likelihood or posterior. However, at present, a significant challenge is assessing how each feature impacts the SBI model's predictions. Here, it was developed an approach to determine feature importance in the context of cortical circuit parameter inference. it was first created a dataset that includes a million distinct simulations from a spiking cortical microcircuit model of recurrently connected excitatory and inhibitory populations. Biophysics-based causal filters were coupled with spikes to generate realistic LFP data. Then, it was extracted a set of meaningful features from simulated LFP data that were used to train an SBI algorithm. To evaluate feature importance, differents tecnichs were used like mutual information (MI), principal component analisis (PCA) and SHAP values, a prominent tool in machine learning for interpreting the contribution of eachfeature to the prediction outcomes. The results demonstrate the effectiveness of this approach in identifying the most critical features for inferring the parameters of a recurrent cortical circuit model based on electrophysiological data. These results were presented at the Brain Informatics 2024 International Conference.File | Dimensione | Formato | |
---|---|---|---|
Sandron_Alessandro.pdf
accesso aperto
Dimensione
3.07 MB
Formato
Adobe PDF
|
3.07 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/72881