Corpus ID: 221083236

Bootstrapping Neural Processes

@article{Lee2020BootstrappingNP,
  title={Bootstrapping Neural Processes},
  author={Juho Lee and Yoonho Lee and Jungtaek Kim and Eunho Yang and Sung Ju Hwang and Y. Teh},
  journal={ArXiv},
  year={2020},
  volume={abs/2008.02956}
}
Unlike in the traditional statistical modeling for which a user typically hand-specify a prior, Neural Processes (NPs) implicitly define a broad class of stochastic processes with neural networks. Given a data stream, NP learns a stochastic process that best describes the data. While this "data-driven" way of learning stochastic processes has proven to handle various types of data, NPs still rely on an assumption that uncertainty in stochastic processes is modeled by a single latent variable… Expand

References

SHOWING 1-10 OF 31 REFERENCES
Neural Processes
The Functional Neural Process
Conditional Neural Processes
Sequential Neural Processes
Attentive Neural Processes
Recurrent Neural Processes
Empirical Evaluation of Neural Process Objectives
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Importance Weighted Autoencoders
Towards a Neural Statistician
...
1
2
3
4
...