Uncertainty through Sampling: The Correspondence of Monte Carlo Dropout and Spiking in Artificial Neural Networks

@inproceedings{Standvoss2019UncertaintyTS,
  title={Uncertainty through Sampling: The Correspondence of Monte Carlo Dropout and Spiking in Artificial Neural Networks},
  author={K. Standvoss and Lukas Gro{\ss}berger},
  year={2019}
}
Any organism that senses its environment only has an incomplete and noisy perspective on the world, which creates a necessity for nervous systems to represent uncertainty. While the principles of encoding uncertainty in biological neural ensembles are still under investigation, deep learning became a popular and effective machine learning method. In these models, sampling through dropout has been proposed as a mechanism to encode uncertainty. Moreover, dropout has previously been linked to… Expand

References

SHOWING 1-10 OF 14 REFERENCES
Spiking Deep Networks with LIF Neurons
Neural Variability and Sampling-Based Probabilistic Representations in the Visual Cortex
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Bayesian models: the structure of the world, uncertainty, behavior, and the brain
Deep Neural Networks as Scientific Models
The dropout learning algorithm
Understanding Measures of Uncertainty for Adversarial Example Detection
...
1
2
...