Re:Reverse Engineering a Neural Network's Clever Solution to...
by dahart on Saturday November 08, 2025 @09:45AM
(#45856958)
Is that the number of adds that don’t overflow an 8-bit result?
On that hunch, I just checked and I get 32896.
Edit: if I exclude either input being zero, I get 32385.
You also get the same number when including input zeros but excluding results above 253. But I’d bet on the author’s reason being filtering of input zeros. Maybe the NN does something bad with zeros, maybe can’t learn them for some reason.
Re:Reverse Engineering a Neural Network's Clever Solution to...
by jtsiskin on Saturday November 08, 2025 @10:24AM
(#45857267)
Interesting puzzle. 32385 is 255 pick 2. My guess would be, to hopefully make interpretation easier, they always had the larger number on one side. So (1,2) but not (2,1). And also 0 wasn’t included. So perhaps their generation loop looks like [[(i,j) for j (i-1 -> 1) for i (256 -> 1)]
Re:Reverse Engineering a Neural Network's Clever Solution to...
by joshribakoff on Saturday November 08, 2025 @11:12AM
(#45857699)
You are potentially conflating combinations with permutations.
Looking later there's also a strange DAC that gives the lowest resistance to the least significant bit, thus making it the biggest contributor to the output. Very confusing.