Nyhetsflöde
Logga in till din kurswebb
Du är inte inloggad på KTH så innehållet är inte anpassat efter dina val.
Har du frågor om kursen?
Om du är registrerad på en aktuell kursomgång, se kursrummet i Canvas. Du hittar rätt kursrum under "Kurser" i personliga menyn.
Är du inte registrerad, se Kurs-PM för DD2380 eller kontakta din studentexpedition, studievägledare, eller utbilningskansli.
I Nyhetsflödet hittar du uppdateringar på sidor, schema och inlägg från lärare (när de även behöver nå tidigare registrerade studenter).
That's very nice :)
Thanks for the feedback! There are now instructions available on how to build the Visualizer on Windows, OS X and Linux. Let me know if you run into problems. I hope this will benefit someone. :)
Anders Sjöqvist korrigerade 30 januari 2016
I've created a graphical visualizer for HW1 (Checkers). It runs the players as child processes, stores their output and lets you step backwards and forwards between the moves. You can find it in the GitHub repo aliqusjoqvist/kth-ai14-checkers-visualizer, along with some documentation and a screenshot of the interface. Feel free to try it if you want. If you do, I'd appreciate feedback. Thanks!
No. As you can see here https://www.kth.se/student/program/kursval/modulschema-1.545551 the the new module schedule system has time slots after 17 and the ai course had one of those. Sorry
Great. And I assume attendance is required?
Attendance only required to present homework assignments and project work but you have some influence over when this takes place.
Daan Wynen korrigerade 14 oktober 2013
Hey all,
I am having some issues with NaNs in my HMM implememntation and wonder if anzybodzy has come across this or even better knows a solution. I pretty much follow Stamp's tutorial to the letter but sometimes I get a situation where during the last iteration of the alpha pass, either all alphas or values of B for this step isare zero, resulting in a zero sum of all alphas, whihch in turn results in an infinite scaling factor.
Now in the alpha pass I don't really notice this since 0 * infinity = 0.
This problem only shows up further down the line where I use the scaling factor in the beta pass, multiplying with it and getting an all-NaN beta array.
I found this post from 2004 with someone having the very same problem while using the stamp pseudocode. This suggests to me that ...
* The pseudocode still has a problem/bug regarding numerical stability OR
* This is to be expected OR
* I made the same mistake as other people ( I know of at least two).
Using this implementation I am still able to get a 200points score though since it doesn't happen every time.
Does anybody have pointers to where the problem might lie?
Dear Daan,
did you solve the problem?
Not so far, no... :(
I had a similar problem and also used the stamp tutorial. The problem seemed to be and it sounds as if you are having the same problem that you try to determine the probability of an impossible sequence according to the hmm you have. There is two quite easy ways around this. You could either adjust your forward algorithm to handle this case or you could make sure there is never zeros in your matrices in which case you will only get very low probabilities instead.
Test comment.
Test successful, Dr. Calvin.
Some day they'll have secrets.
Some day they'll have dreams.
I'm sorry. My responses are limited. You must ask the right questions.
This system desperately needs a "like" button for comments :D
Hej Anders,
Just started working on this assignment and I feel this is going to be really helpful, thanks!