2019 February 25¶
Location: Coors Tech¶
Attending:¶
Thomas Iga Jihyun Bane Hayden Andy Antoine
Key takeaways¶
- Hayden has lots of feedback in the comments.
Problems¶
- Hayden has a ridiculously high number of feature dimensions
- How to validate with low number of wells?
- If trained successfully, would a model from here work in the field?
Comments¶
- Polar coordinate interpolation to avoid nans
- PCA to reduce dimensionality
- Multi-dimensional scaling for data dimensionality reduction
- Check error on slide 4 (normalize between -1 and 1)
- A super low training loss may indicate over training.
- Consider cross-validating across wells and models per well.
- A dropout layer may help you reduce over training.
- Consider leveraging spatial correlation with convolutional layers.
- Space filling curves may help reorder cells into an ordered 1D sequence.
- Consider autoencoding data then training network (alternative to PCA).
- Consider intelligently selecting validation set (not randomly).
Topics of discussion for next week¶
- Bin will discuss his project and get feedback