Search NASA⌕ Search

SEARCH · Search NASA

Results for “criminal justice system”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

2 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

COVID-19 Impact on Prison Population and Flow Dynamics

The goal of this project was to develop a unique, high-level, concept model that will (1) help examine the consequences COVID-19 has had on prison population and flow dynamics in Illinois and (2) explore (to the extent possible) how that will unfold in the short- and mid-term future. Argonne has unique expertise in dynamic systems modeling and highly specialized simulation capabilities, which will be helpful in developing such a model. The ultimate objective of this CRADA is to develop with the Illinois Public Sentencing Policy Advisory Council (SPAC) the capability to identify and understand factors and interactions associated with prison population and flow dynamics in Illinois. This understanding will then potentially lead to improvements in the allocation of various resources and services. This approach would also be useful to all other states.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗