mml-book / mml-book.github.io

Companion webpage to the book "Mathematics For Machine Learning"
12.71k stars 2.36k forks source link

Concatenated Random Variable States (2) #767

Closed ckwastra closed 6 months ago

ckwastra commented 6 months ago

Describe the mistake In the provided text:

... To consider the effect of applying the sum rule of probability and the effect of conditioning, we explicitly write the Gaussian distribution in terms of the concatenated states $[\boldsymbol{x}^\top, \boldsymbol{y}^\top]$, ...

I believe it maintains greater consistency to employ ${[\boldsymbol{x}^\top, \boldsymbol{y}^\top]}^\top$ as the notation for the concatenated states. In this context, we concatenate two column vectors to create a new column vector. While this notation was suggested in #513, the notation $[\boldsymbol{x}^\top, \boldsymbol{y}^\top]$ (without the transpose of the row vector) was ultimately adopted. Any clarification on this matter is appreciated.

Location

  1. Draft (2023-12-19)
  2. Chapter 6
  3. Page 199
  4. Line 3

Proposed solution Change $[\boldsymbol{x}^\top, \boldsymbol{y}^\top]$ to ${[\boldsymbol{x}^\top, \boldsymbol{y}^\top]}^\top$ in the above text.

mpd37 commented 6 months ago

Thanks. #513 was insufficiently resolved. That was a typo at our end. Will fix this now.