PCA might be good too.
-
-
nice, thanks! Other stuff I've on my list is random walks, signal detection theory, and basic strategies from economic games (e.g. win stay lose shift).
1 reply 0 retweets 2 likes -
Game of Life and other cellular automata are simple and useful too.
1 reply 0 retweets 3 likes -
Maybe Take The Best as a simple heuristic model? I guess Bayes rule is simple enough too.
1 reply 0 retweets 3 likes -
A Boltzmann Machine might be simple enough? Not sure... I might be pushing it here though.
2 replies 0 retweets 4 likes -
Interesting idea. the students will be pretty savvy, but I'd like to present models that can be compared to actual human performance in cognitive tasks (ideally in more than one cognitive domain). I'll need to read more on where it's been used.
1 reply 0 retweets 1 like -
Boltzmann Machines can certainly be used to model behavioural data. I've done it.
1 reply 0 retweets 1 like -
ref? Thanks!
1 reply 0 retweets 1 like -
I used them as an alternative implementation for hub-and-spoke model by Rogers et 2004. But they are extremely flexible. It's like asking me what a FF network can capture. Anything!
1 reply 0 retweets 1 like -
*not really anything but you get my drift
1 reply 0 retweets 1 like
Here's a great vintage (ten years is very long for deep nets) talk on RBMs by Hinton. https://youtu.be/AyzOUbkUf3M
-
-
Shows them able to do number recognition.
0 replies 0 retweets 1 likeThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.