|
|
|
|
|
|
0 Replies and 567 Views
First Principle and Neural Network Implementation 567 0
Started by Patrick Ng
This thread aims at linking first principle to deeper understanding of neural network implementation. First principle first, in both Unconventional and classic producing area, typical IP distribution is anything but a bell curve. For example, http://aemstatic-ww2.azureedge.net/content/dam/ogfj/print-articles/volume-13/issue-12/1612OGFJng-z01.jpg.scale.LARGE.jpg Recall geology fundamental, grain size distribution of sediments is also log normal. It suffices to reason that using...
|
|
|
|
0 |
567 |
02 Oct 2017 11:11 PM |
|
0 Replies and 830 Views
Something for Everyone 830 0
Started by Patrick Ng
For those who got flooded by Harvey or from “control release”, our thoughts and prayers are with you. As I was stuck at the house when Harvey was pouring down 51 inches of rain, surrounded by flooded streets and freeways, I thought about what would make this blog relevant to our members. I recall: a) the first time many machine and deep learning jargons appear daunting, b) after internal translation of machine learning speak to G&G experience, I can relate to much better. So here are three ...
|
|
|
|
0 |
830 |
05 Sep 2017 11:07 PM |
|
0 Replies and 591 Views
Deep Learning online from one of the best teachers 591 0
Started by Patrick Ng
While AI / Deep Learning appears daunting, a new online course by Prof Andrew Ng may just be a good starting point. It will cover TensorFlow. For more detailed information, see https://techcrunch.com/2017/08/08/deeplearning-ai-is-andrew-ngs-new-series-of-deep-learning-classes-on-coursera/
|
|
|
|
0 |
591 |
11 Aug 2017 12:30 AM |
|
1 Replies and 764 Views
Different Approach with a Common Thread - Use of First Principle 764 1
Started by Patrick Ng
Two articles illustrate with examples of creating tangible value: 1) DNN - https://www.onepetro.org/conference-paper/SPE-174799-MS 2) Multivariate - https://info.drillinginfo.com/machine-learning-in-oil-and-gas/ Food for thought - with infusion of G&G, learning with machine beats machine modeling alone
|
|
|
|
1 |
764 |
|
|
1 Replies and 999 Views
May 22, 2017 Workshop Follow-up - Mining Big Data 999 1
Started by Patrick Ng
Recall in Deborah Sacrey's presentation, neural network was able to seek out features from 2-ms data, but not 4-ms, when 2-ms is resampled from 4-ms data. For some, that was puzzling. Q1: is such observation common, and if so, is there a simple explanation Q2: what is the implication on Deep Learning and sampling rate Thanks in advance.
|
|
|
|
1 |
999 |
|