Nyhetsflöde
Logga in till din kurswebb
Du är inte inloggad på KTH så innehållet är inte anpassat efter dina val.
I Nyhetsflödet hittar du uppdateringar på sidor, schema och inlägg från lärare (när de även behöver nå tidigare registrerade studenter).
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 sjoqvist/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!
Visa tidigare händelser (4)
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!
Augusti 2015
I see that the preliminary schedule contains a lot of lectures and labs after 17.00, this will be changed right?
Visa tidigare händelser (3)
September 2014
Anyone else interested in working in Apple's Swift and/or generating Japanese for the project?
Oktober 2013
Hey all,
I am having some issues with NaNs in my HMM implementation and wonder if anybody 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 are zero, resulting in a zero sum of all alphas, which 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?
Visa tidigare händelser (4)
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?
September 2013
Hi,
we are a group of 3 looking for one last student to join us for the final project. We aim for the maximum grade and we are likely going to use C++.
contact me at: lucagi@kth.se
Luca
Visa tidigare händelser (1)
Visa tidigare händelser (5)
Hej Anders,
Just started working on this assignment and I feel this is going to be really helpful, thanks!