addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwchatcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-crosscrosseditemptyheartfacebookfolderfullheartglobegmailgoogleimagesinstagramlinklocation-pinmagnifying-glassmailminusmoremuplabelShape 3 + Rectangle 1outlookpersonplusprice-ribbonImported LayersImported LayersImported Layersshieldstartrashtriangle-downtriangle-uptwitteruseryahoo

Re: [Cleveland-AI-ML-support-group] ML tracks

From: Joe
Sent on: Sunday, October 16, 2011 8:37 PM
 Welcome new member Shruti. For those of you who were thinking of signing up for the ML advanced track but where reluctant, you may want to reconsider, because the homework is fairly easy. You get to keep answering it every 10 minutes until you get a 100 score, and it explains all the answers every time. Doing that with google search help is a pretty good way to learn the material in addition to the videos.

 Below are the answers to my earlier questions.

--- On Sun, 10/16/11, Joe <[address removed]> wrote:

> From: Joe <[address removed]>
> Subject: Re: [Cleveland-AI-ML-sup­port-group] BFS, UCS, A*
> To: [address removed]
> Date: Sunday, October 16, 2011, 4:00 PM
>  Yesterday we had a pretty useful
> discussion about what type of objects are in the frontier
> data structure of the A* pseudo code. Reviewing the videos
> while working on the homework, I came up with a few
> questions that helped me to check my understanding of the
> breadth first search pseudo code, which is very similar to
> UCS and A* pseudo code also. I have some answers in mind to
> these questions which I think are correct, but I wanted to
> give the group a chance to answer first. I created a blog
> post about it:
> While studying this weeks lectures, I created
> a few questions that helped me to understand breadth first
> search as described in the videos. Here is the pseudo code
> for BFS from video ‘unit 2 topic 6 graph search’:
> function graph-search(problem­)
> frontier= {[initial]}
> explored={}
> loop:
> if frontier empty: return Fail
> path=remove-choice(f­rontier)
> s=path.end
> add s to explored
> if s is a goal: return path
> for a in actions:
> add [path + a-> Result(s,a)] to frontier,
> unless Result(s,a) in frontier or explored
> The illuminating questions are:

> What does a->Result(s,a) return? answer: one new one step path, which is a list of 2 city names.

> What does Result(s,a) return? answer: a city name, the second of the 2 city names returned by a->Result(s,a).

> What is frontier a list of? answer: paths, which are a list of 2 or more city names.

> What is unusual about checking if Result(s,a) is in
> frontier? answer: frontier is a list of paths but your searching for a city name, so your searching for strings within a list of lists.

> What is ‘actions’? answer: a list of potential 1 step paths from a city.

> What do these two facts imply about a map that has a loop
> in it? answer: the algorithm will not create paths with loops in them. (the word 'two' was a mistake)
> Joe

Our Sponsors

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy