TY  - Type of reference 
TI  - Context-Dependent Deep Learning 
AU  - Roy M. Turner 
AU  - Cynthia Loftin 
AU  - Alexander Revello 
AU  - Logan R. Kline 
AU  - Meredith A. Lewis 
AU  - Salimeh Yasaei Sekeh 
AB  - 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. 
DO  - 10.21494/ISTE.OP.2021.0690 
JF  - Modeling and Using Context 
KW  - Deep learning,  Neural Networks,  context-mediated behavior,  object detection,  image recognition, Apprentissage, profond,  réseaux de neurones,  comportement médiatisé par le contexte,  détection d’objets,  reconnaissance d’image,  
L1  - https://openscience.fr/IMG/pdf/iste_muc21v4n1_8.pdf 
LA  - en 
PB  - ISTE OpenScience 
DA  - 2021/07/1 
SN  - 2514-5711 
TT  - Apprentissage en Profondeur Dépendant du Contexte 
UR  - https://openscience.fr/Context-Dependent-Deep-Learning 
IS  - CONTEXT-21 Special Issue 
VL  - 4 
ER  -