...using "non-judicial variables" like age, sex, and race. Harper and computer scientist Stamos Karamouzis, who developed the network, reconstructed the profiles of more than 1,300 death row inmates from a national population using simple attributes such as race, sex, age and highest year of education when first imprisoned for a capital offense.
"We took a thousand of those profiles and used them to 'train' the network," says Harper.
They then tested the system using 300 profiles the network had never seen. It predicted the execution and non-execution rate with greater than 90% accuracy.
# posted by
Gerry Canavan @ 10:00 AM
|