Re:Gaussian Processes for Machine Learning (2010)
by karthiktharava on Sunday July 22, 2018 @12:07PM
(#17587384)
Being a non parametric model, they are pretty garbage for generalizations outside of the domain of the data they have "seen" and they are also not very data efficient. One area where I have seen success for them is when they are applied to automatic hyper-parameter selection for neural networks.
[ Parent
| on HN ]
Re:Gaussian Processes for Machine Learning (2010)
by 317070 on Sunday July 22, 2018 @03:33PM
(#17588451)
It's the opposite, they are very data efficient (compared to neural networks). Also, they are a bayesian method and give some mathematical guarantees. They are computationally expensive though. You can use them in neural nets to do few shot learning [0].
[0] https://arxiv.org/pdf/1802.07535.pdf or https://arxiv.org/abs/1807.01622