Can this be rearranged to solve?

  • Context: Graduate 
  • Thread starter Thread starter jeff91
  • Start date Start date
Click For Summary

Discussion Overview

The discussion revolves around the possibility of rearranging or inverting a mathematical expression to solve for p(1X | Y) within the context of Bayesian networks and AHP (Analytic Hierarchy Process) questionnaires. Participants explore the implications of the notation and the structure of the equations involved.

Discussion Character

  • Technical explanation
  • Conceptual clarification
  • Debate/contested

Main Points Raised

  • One participant inquires about rearranging the expression to solve for p(1X | Y) but expresses uncertainty due to a long absence from advanced mathematics.
  • Another participant questions the notation and suggests that the problem may involve solving for a matrix given two column vectors.
  • A different participant notes that if p(1X | Y) is a scalar, it could be trivial to solve, but if it is an mxm matrix, there may not be enough information to determine it uniquely.
  • One participant speculates that the context may relate to a neural network and Bayesian probability.
  • A later reply clarifies that the participant is attempting to derive probabilities for a Bayesian network from an AHP questionnaire, indicating the use of weights from an AHP spreadsheet.
  • Another participant asserts that if p(1X | Y) is indeed an mxm matrix, it cannot be inverted, as multiple matrices could yield the same results for the given vectors.

Areas of Agreement / Disagreement

Participants express varying levels of understanding regarding the notation and the mathematical structure involved. There is no consensus on whether the problem can be solved or inverted, with some asserting it cannot be uniquely determined while others suggest potential trivial solutions under certain conditions.

Contextual Notes

Participants highlight the ambiguity in the notation and the dependence on whether p(1X | Y) is a scalar or a matrix. The discussion reflects limitations in the information provided and the assumptions about the mathematical relationships involved.

jeff91
Messages
2
Reaction score
0
Is it possible to rearrange or inverse this to solve for p(1X | Y)? I haven't done this level of maths for over 15 years and haven't a clue where to start.

1wk =p(1X | Y)⋅ wk

weight vector of 1X node in case a is 1w=[1w1, 1w2,…, 1wm]
weight vector of Y node w=[w1, w2,…, wm]

where 1 ≤ k ≤ m
 
Physics news on Phys.org
I don't understand the notation. Are you asking about solving an equation of the form:

<n-dimensional column vector> = <n by n matrix> < another n-dimensional column vector>

You want to solve for the matrix when given the two column vectors?
 
  • Like
Likes   Reactions: jeff91
I don't understand the notation either.
If p(1X | Y) is a scalar then it's trivial to solve (you have m equations that should all lead to the same scalar, excluding possible lines that are 0=p*0). If it is an mxm matrix then there is not enough information to determine it uniquely.
 
  • Like
Likes   Reactions: jeff91
What is the context of your problem? It looks like something related to a neural net where the p(X|Y) is some kind of Baysian probability
 
  • Like
Likes   Reactions: jeff91
Thank you for your replies. I am trying to obtain probabilities to put in a Bayesian network from an AHP questionnaire.
This is the bit from the book I am looking at.
1596886909421.png

I have the weights as they are outputted from the AHP spreadsheet.
I have only ever done Bayesian networks when I have been supplied with the probabilities.
 
It's an mxm matrix then. No, you can't invert that problem. There are many different matrices that will lead to the same result for given vectors 1wk and wk.
 
  • Like
Likes   Reactions: jeff91

Similar threads

  • · Replies 2 ·
Replies
2
Views
2K
Replies
2
Views
3K
  • · Replies 2 ·
Replies
2
Views
2K
  • · Replies 2 ·
Replies
2
Views
3K
  • · Replies 114 ·
4
Replies
114
Views
12K
  • · Replies 2 ·
Replies
2
Views
3K
  • · Replies 8 ·
Replies
8
Views
2K
  • · Replies 8 ·
Replies
8
Views
22K
  • · Replies 42 ·
2
Replies
42
Views
11K
  • · Replies 2 ·
Replies
2
Views
2K