I program by day, and program some more by night. I just finished Go Scoring Camera, an Android app that does computer vision to interpret Go boards, and I’m starting on Keyboard Builder, a tool for customizing the Android Phones’ on-screen keyboard. I’ll keep writing phone apps until they’re sufficient to provide a passive income.
I think I mentioned it before, but you could go further with the Go computer vision thing—Ken Thompson considerably improved OCR results for scanning chess books by adding in domain-specific knowledge (about chess): http://doc.cat-v.org/bell_labs/reading_chess/
To expand my Go comment (did I say this somewhere else? I feel like I did but I can’t find it), what I mean is that you could generate possible configurations and rank them by their semantic content
For example, you could feed each possible configuration through GNU Go, asking it to score the configurations, and pick the configuration which is most ‘intelligent’/likely to be produced by strong scorers.
Or, you could instead tell GNU Go that ‘black is a 20 kyu player, white is 1 dan’ and rank configurations by which configuration is most consistent with such a differential (configurations with stupid moves by black being far more likely than stupid moves by white, and the converse).
I program by day, and program some more by night. I just finished Go Scoring Camera, an Android app that does computer vision to interpret Go boards, and I’m starting on Keyboard Builder, a tool for customizing the Android Phones’ on-screen keyboard. I’ll keep writing phone apps until they’re sufficient to provide a passive income.
I think I mentioned it before, but you could go further with the Go computer vision thing—Ken Thompson considerably improved OCR results for scanning chess books by adding in domain-specific knowledge (about chess): http://doc.cat-v.org/bell_labs/reading_chess/
+1 for “I program by day, and program some more by night.”
He’s a programmer, and he’s okay; he hacks by night, programs by day...
To expand my Go comment (did I say this somewhere else? I feel like I did but I can’t find it), what I mean is that you could generate possible configurations and rank them by their semantic content
For example, you could feed each possible configuration through GNU Go, asking it to score the configurations, and pick the configuration which is most ‘intelligent’/likely to be produced by strong scorers. Or, you could instead tell GNU Go that ‘black is a 20 kyu player, white is 1 dan’ and rank configurations by which configuration is most consistent with such a differential (configurations with stupid moves by black being far more likely than stupid moves by white, and the converse).