@ARTICLE{10.21494/ISTE.OP.2021.0690, TITLE={Context-Dependent Deep Learning}, AUTHOR={Roy M. Turner, Cynthia Loftin, Alexander Revello, Logan R. Kline, Meredith A. Lewis, Salimeh Yasaei Sekeh, }, JOURNAL={Modeling and Using Context}, VOLUME={4}, NUMBER={CONTEXT-21 Special Issue}, YEAR={2021}, URL={https://www.openscience.fr/Context-Dependent-Deep-Learning}, DOI={10.21494/ISTE.OP.2021.0690}, ISSN={2514-5711}, ABSTRACT={Explicitly representing an agent’s context has been shown to have many benefits, which should also apply to machine learning. In this paper, we describe an approach to do this called context-dependent deep learning (CDDL), which is based on earlier work in context-mediated behavior (CMB) that uses contextual schemas (c-schemas) to represent classes of situations along with knowledge useful in them. These c-schemas are then recalled and guide reasoning in the corresponding contexts. CDDL stores knowledge about deep neural network structure and weights in c-schemas, which allows context-specific learning. Our work is being developed in the domain of seabird detection in aerial images of islands for use by biologists.}}