Ontology highlight
ABSTRACT:
SUBMITTER: Dezfouli A
PROVIDER: S-EPMC7682379 | biostudies-literature | 2020 Nov
REPOSITORIES: biostudies-literature
Proceedings of the National Academy of Sciences of the United States of America 20201104 46
Adversarial examples are carefully crafted input patterns that are surprisingly poorly classified by artificial and/or natural neural networks. Here we examine adversarial vulnerabilities in the processes responsible for learning and choice in humans. Building upon recent recurrent neural network models of choice processes, we propose a general framework for generating adversarial opponents that can shape the choices of individuals in particular decision-making tasks toward the behavioral patter ...[more]