Course talk:CPSC522/Particle Filtering

Hey Arthur,

Great page.

Your coverage of the statistical foundation is awesome, but I can't help but feel some of the terms used here can be made simpler for the CS students. Since this page is named "particle filtering" instead of "sequential Monte Carlo" , the large amount of big stats-y terms may be able to be reduced. A picture of the graphical model can be very helpful in explaining recursive estimation. Also, was the filtering problem described somewhere?

A couple math equations may be helpful in the prerequisite sections. The mentioning of a posterior distribution without describing what is being conditioned on (some observations) makes the word "posterior" somewhat vacuous in the Bayesian estimation section. The actual posterior distribution is only given later in the mathematical model section, but it may be a good idea to put it in the prereq sections, as a build-up to the actual PF formulation.

In the PF algorithm section, the terms "random variable", "sample", and "particle" seem to be used interchangeably, and may confuse readers who don't know they're referring to the same concept.

The example is quite well written, but perhaps relating some of the English terms to (or re-formulating the explanation in terms of) the previous $x$'s and $Z$'s. Also, I think a moving gif would be a lot better than the still-image.

Thanks for the good read, Ricky

• (5) The topic is relevant for the course.
• (4) The writing is clear and the English is good.
• (4) The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds).
• (4) The formalism (definitions, mathematics) was well chosen to make the page easier to understand.
• (4) The abstract is a concise and clear summary.
• (4.5) There were appropriate (original) examples that helped make the topic clear.
• (3) There was appropriate use of (pseudo-) code.
• (5) It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic).
• (5) It is correct.
• (4) It was neither too short nor too long for the topic.
• (4) It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page).
• (3) It links to appropriate other pages in the wiki.
• (5) The references and links to external pages are well chosen.
• (4) I would recommend this page to someone who wanted to find out about the topic.
• (3) This page should be highlighted as an exemplary page for others to emulate.

Hi Chen

Thank you for your reply about our wiki and I have already changed most of its part and added pseudo code for general particle filtering algorithm. For the technical terms, I will change that accordingly. Thank you

Regards Arthur

Hi Arthur,

It is glad to read your page, it helps me a lot in understanding Particle Filtering. Only a few suggestions:

1. Use latex to represent formulas might be better.

2. The citation needs to be improved, maybe you can refer to some Wikipedia pages.

3. The "Builds on" section is not clear, I think it would be better if you can give some examples of previous probability model here.

4. In Prerequisite II: Bayesian Estimation, you left "(pdf)" in the first sentence, I think you might forget to give a link here.

5. There are are some "k" besides variable name should be written a subscript, I suggest to use latex instead of pictures to easily handle this.

Best regards,

Jiahong Chen

Hi Chen,

Nice to hear from you about your suggestions and I have already modified all the math formulas using the Latex for clear understanding. Thank you

Plus, small mistakes have already been checked.

Once again thank you for your suggestion!

Regards Arthur

Hi Arthur,

Thanks for your informative page. One thing that I liked about your wiki page was that you mentioned lots of applications and that is great.

Here are a few suggestions for you to think of:

1. It was better to type formulae, rather than putting a picture of them.

2. The English can improve. There are some typos and some unclear parts in the page.

3. It is better to have all references at the end. Then people can easily access the authors or the published date of the papers.

4. It would be nice to have a pseudo-code of particle filtering algorithm and an example with images to explain that.

Cheers,

Bahare

Dear Bahare Thank you for your great support for pointing out the problems my wiki page has and I am trying to fixing it up to improve it much better.

1. For the pseudo-code for general particle filtering. I have already added it to the relevent part with explanation in it.

2. For the references part, I have already put all the references in the end of the wiki page.

3. For the English part, I have already double checked with the wording.

Thanks for your advice. Arthur

Hello Arthur,

First, let me thank you for contributing to this Wiki. There are a lot of bright points on your page, and I like most of the parts and their content, but there are a few points that came to my mind that I want to suggest you. 1) You might wanna add a "More General Than" part in your page, I believe it is part of the template that Dr. Poole suggested and personally I think it is a useful thing to have on a wiki page. 2) In your "Prerequisite II" part, there is a hyperlink in a wrong format "https://en.wikipedia.org/wiki/Monte_Carlo_method" 3) The page lacks links to other wiki pages 4) In the "Mathematical Model" there is an uploaded file in a wrong format: File:Mathematical Formula 5.png 5) There is no Bibliography section. It is worth mentioning that in academic world, the bibliography part gives credit to an article, and when it lacks, decreases the validity of the article. 6) It might be good to include the "To Add" section at the end so the next contributors can understand which areas are good to work and develop 7) I believe it is better if you put the links and authors at the bibliography section rather than putting some PDFs in your content

These were the points that came to my mind while reading your page.

Mehrdad Ghomi

Hello Mehrdad Ghomi,

Nice to here from you about your points about my wiki page 1) You might wanna add a "More General Than" part in your page, I believe it is part of the template that Dr. Poole suggested and personally I think it is a useful thing to have on a wiki page. -- Overview tab already added in the abstract part. 2) In your "Prerequisite II" part, there is a hyperlink in a wrong format "https://en.wikipedia.org/wiki/Monte_Carlo_method" -- Changed already 3) The page lacks links to other wiki pages --added in the Related Wiki Page Session --added already 4) In the "Mathematical Model" there is an uploaded file in a wrong format: File:Mathematical Formula 5.png --changed already 5) There is no Bibliography section. It is worth mentioning that in academic world, the bibliography part gives credit to an article, and when it lacks, decreases the validity of the article. --added already 6) It might be good to include the "To Add" section at the end so the next contributors can understand which areas are good to work and develop --added already. 7) I believe it is better if you put the links and authors at the bibliography section rather than putting some PDFs in your content -- I will change that.

Thank you very much