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
Search this discussion:
Search
You are not authorized to create a new topic
Page 2 of 18 << < 12345 > >>
Topics
 Replies
 Views
 Last Post
0 Replies and 50 Views EiD - Probing Questions and Seeking Answers  50  0 Started by  Patrick Ng These three observations can benefit taking feedback / sharing experience from a wider community - 1) Edge computing - lots of applications in edge computing helps us reduce cost and increase efficiency. Edge computing enables cheaper ML model to be built and at different time scales. 2) Knowledge curation - make open-source movement useful, we need to organize information in one place (reservoir, geoscience, engineering) and make that searchable like Yahoo! in the early days of i...
0 50
16 Apr 2021 01:41 PM
0 Replies and 41 Views Energy in Data 2021 - Greeting  41  0 Started by  Patrick Ng Thinking about the two-morning workshop https://www.youtube.com/watchv=t53OXaV_5M8 It is a click away. https://energyindata.org/
0 41
08 Apr 2021 12:16 PM
0 Replies and 68 Views First look at well production data - before tackling how well ML models generalize?  68  0 Started by  Patrick Ng Follow up to prior post “AI teaches itself - no manual labels required” 03.08.2021. Perspective - day in and day out, geologists, engineers, and analysts are active players in asset evaluation and project economics. 80 of the time spent on generating oil and gas projects: exploring ideas with a map, finalizing investment decisions and picking well locations on a map. And what else we may do the other 20 Due diligence and risk assessment. A common issue is the time and effort it takes to p...
0 68
15 Mar 2021 01:09 PM
0 Replies and 73 Views AI teaches itself - no manual labels required  73  0 Started by  Patrick Ng One billion public-facing Instagram photos were used to train an algorithm created by Facebook to learn to recognise images by itself. https://www.bbc.com/news/technology-56321296 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 ...
0 73
08 Mar 2021 12:36 PM
0 Replies and 83 Views AI surprised Google developers - tacking like human  83  0 Started by  Patrick Ng https://www.bbc.com/future/article/20210222-how-googles-hot-air-balloon-surprised-its-creators Note - encoding (chaining of alpha-numeric) , e.g., 'Be5' to move a bishop, makes powerful feature engineering when training machine to play chess.
0 83
23 Feb 2021 10:12 PM
You are not authorized to create a new topic
Page 2 of 18 << < 12345 > >>


RSS Feed Available

Moderators

Andrew Munoz Ensign Natural Resources
Patrick Ng Real Core Energy

Headquarters Contacts

Susan Nash Director, Innovation and Emerging Science and Technology breeling