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 08 Mar 2021 12:36 PM by  Patrick Ng
AI teaches itself - no manual labels required
 0 Replies
Join to post a reply.
Author Messages
Patrick Ng
New Member
New Member

08 Mar 2021 12:36 PM
    One billion public-facing Instagram photos were used to train an algorithm created by Facebook to learn to recognise images by itself.

    Implication - it becomes more important than before when embarking on AI / deep learning projects, we shall ensure adequate QC and comprehend the underlying distribution. Understand what goes into the system and be prepared to flag surprises (e.g., what we cannot comfortably explain among ourselves).

    Scenario - say we are working with wells geospatial and temporal data, and perform decline curve analysis (from production history), in setup for supervised Machine Learning, the first task is to label good vs poor performing wells. Now consider these two simple questions:

    Q1: do we label good performer based on initial production or over all volume produced, like EUR?

    Q2: how we may contemplate to train AI to learn to "recognize" and categorize wells by itself?

    Lets start that conversation, and feel free to chime in.

    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