skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 10:00 PM ET on Friday, February 6 until 10:00 AM ET on Saturday, February 7 due to maintenance. We apologize for the inconvenience.


Title: Neural SDE-based Epistemic Uncertainty Quantification in Deep Neural Networks
Award ID(s):
2039014
PAR ID:
10519263
Author(s) / Creator(s):
; ;
Publisher / Repository:
25th International Conference on Engineering Applications of Neural Networks
Date Published:
Format(s):
Medium: X
Location:
Corfu, Greece
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Objective.Optical stimulation ofin vitroneurons requires prior transfection with light gated ion channels. This additional step brings complexity and requires optimization. Simplification of the process will ease the undertaking of studies on biological neural networks needing external stimulation.Approach.We constructed a simple platform where embryonic stem cell derived optogenetic neural spheroids, cultured and maintained separately, can be seeded on top of the primary non-optogenetic neuron cultures.Main results.We found that the primary neural network can be stimulated through the spheroids. This allows making investigations like network response dynamics and pharmacological perturbations possible.Significance.Thus, our platform provides an on-demand method to stimulate neural preparations for many different studies. 
    more » « less
  2. null (Ed.)