Researchers Predict Death Penalty Outcomes
Loyola announcement - March 17, 2005
Loyola University Researchers Predict Death Penalty Outcomes
NEW ORLEANS - Loyola University New Orleans researchers developed, trained, and tested an artificial neural network that is capable of predicting with a high degree of accuracy whether or not a convicted capital offender will or will not be executed.
An artificial neural network (ANN) is a multiprocessor computing system that resembles the way biological nervous systems process information. The main characteristic of such a computing system is the number of highly interconnected processing elements (neurons) working together to solve specific problems without being programmed with step-by-step instructions. Instead ANNs are capable of learning on their own or by example through a learning process that involves adjustments to the connections that exist between the neurons.
"For our project first we reconstructed the profiles of more than 1,300 death row inmates from a national population by using simple attributes such as the inmate's sex, race, and highest year of education completed at time of first imprisonment for capital offense. Then we performed various experiments in order to develop an ANN that is suitable to the profiles. We trained the network by letting it "witness" 1,000 of the profiles more than 100 times each. Finally we tested the ANN using 300 profiles that the network never witnessed before. The network was capable of correctly predicting execution/non-execution at a rate higher than 90%" said Dr. Stamos Karamouzis, associate professor of computer science and developer of the network. Karamouzis stressed, "Although ANNs, are successfully used for data classification problems in various domains this is the first time that such a technology is applied to such a vital and controversial issue."
Dr. Dee Wood Harper, professor of sociology and criminology at Loyola and project co-researcher, commented: "It seems to us that our research can specify the post death conviction process and can add evidence concerning the fairness or unfairness of the process." Harper continues by saying, "Predicting execution outcomes for prisoners under a sentence of death utilizing essential attributes that have no direct bearing on the judicial process has serious implications concerning the fairness of the death penalty."
Details of the network's functionality and implications have been announced in Amsterdam at the 2004 Conference of the European Society of Criminology and in Austria at the 2005 International IASTED Conference on Artificial Intelligence Applications. Additionally, following peer review, the work has been published in February in the edited volume Artificial Intelligence and Applications, published by ACTA Press (M. H.Hamza, Ed.).