Deep Learning/Machine Learning Technical Interest Group (TIG)

Applying new analytics, neural networks, computational approaches using structured and unstructured data, and also training neural networks with supervised and unsupervised algorithms. Chaired by Patrick Ng and Andrew Munoz.
Deep Learning - Machine Learning TIG
PrevPrev Go to previous topic
NextNext Go to next topic
Last Post 18 Feb 2021 01:39 PM by  Patrick Ng
How well do ML models generalize?
 0 Replies
Join to post a reply.
Author Messages
Patrick Ng
New Member
New Member

18 Feb 2021 01:39 PM
    One word - underspecification.

    Perspective - draw analogy between geophysical data processing (wiener-levinson,, homomorphic and minimum-entropy deconvolution) and ML models (logistic regression, neural network, LSTM, GAN), their ability to generalize depends on data. Both use statistics, both are straightforward to execute once implemented on a computer. But getting consistent results is anything but. Heard of the phase “it is more an art than science”?

    "Art" is attributable to how well a deconvolution algorithm or ML model works on a certain subset of data, a type of distribution (shape of underlying variance), or on slightly adulterated data (often for convenience, e.g., auto-scaling to minimize influence of noise or undersampling).

    By attending focused workshops and sampling across sessions, we may learn actionable practical tools to diagnose before-and-after results to narrow down the avenues for further investigation. So instead of tackling 3 different techniques, 5 independent variations and 10 hyperparameters, say an awesome 150 pressing combinations, we become wiser in adapting fail-fast approach to home in on the most promising selections. EiD 2021 can help us develop a framework to deliver ML result consistency and a close loop for rapid cross-discipline engagement to tackle the energy storage challenge (highlighted by Texas freeze out). Compress cycle time and deliver cost savings.
    Join to post a reply.


    Andrew Munoz Ensign Natural Resources
    Patrick Ng Real Core Energy

    Headquarters Contacts

    Susan Nash Director, Innovation and Emerging Science and Technology breeling