|
|
|
|
|
|
0 Replies and 612 Views
First Step to AI 612 0
Started by Patrick Ng
As 2017 comes to a close and 2018 is just around the corner, why don't we take a stab at AI TensorFlow and Deep Learning emphasize programming and experimentation. Geoscientists can make a real difference in designing how we interact with machine – AI front end. As an example, imagine you can “talk” to Echo back and forth and ask Alexa about a particular basin. We use Amazon Alexa Skills Kit (ASK) and role play with “Basin Bot” as follows: You: “Alexa start Basin Bot” A...
|
|
|
|
0 |
612 |
30 Dec 2017 01:28 AM |
|
1 Replies and 637 Views
AAPG Business Meeting Leadership Days Live 637 1
Started by Patrick Ng
Lets make this TIG a go-to place for outside the box thinking and help AAPG plan for the next 100 years. For warm up, post your answers to: Q1: what do we do today to show value Q2: new venture strategy - number of super vs. mini-basins Q3: kind of data that we need to be successful All ideas welcome! Let your creativity rip, fast and furious.
|
|
|
|
1 |
637 |
|
|
0 Replies and 668 Views
Model Non-Uniqueness and First Principle 668 0
Started by Patrick Ng
In classic model-based inversion, we learn to live with non-unique solution (i.e., there is more than one model that fit the data using criteria like minimum mean squared error). One safeguard is calibration (e.g., seismic-inverted model properties vs. that from well logs or drill bits) to determine if the resulting model makes sense or not. Likewise, we can have different neural network configurations (e.g., number of hidden layers and neurons within each layer, even different activation fun...
|
|
|
|
0 |
668 |
17 Nov 2017 11:18 AM |
|
0 Replies and 574 Views
TensorFlow in the Cloud - AWS, GCP or Azure? 574 0
Started by Patrick Ng
TensorFlow on three platforms, first impression - Amazon Web Services (AWS) - does require use of Unix script, and if running from Windows, additional download of utility PuTTY for ssh connections (geek speak for cybersecurity key). ttps://www.datacamp.com/community/tutorials/deep-learning-jupyter-aws Google Cloud Platform (GCP) - much the same as AWS, and no PuTTY download required. https://towardsdatascience.com/running-jupyter-notebook-in-google-cloud-platform-in-15-min-61e16da34d52 ...
|
|
|
|
0 |
574 |
16 Nov 2017 03:22 PM |
|
1 Replies and 575 Views
First Principle - Model 575 1
Started by Patrick Ng
Recall what 'model' meant and lessons learnt: Amplitude-versus-Offset (AVO) Intercept and slope (gradient) multiplied by sine square of angle in a linearised model Product of intercept and slope is an attribute (e.g., feature engineering) Intercept and slope are two distinct features Inversion Gulf coast - low-frequency trend / young clastic sediments / cyclic deposition North Sea - discrete-structure layers / carbonates / unconformities Prestack Depth Migration GOM - vel...
|
|
|
|
1 |
575 |
|