TY - JOUR
T1 - CBCL-PR
T2 - A Cognitively Inspired Model for Class-Incremental Learning in Robotics
AU - Ayub, Ali
AU - Wagner, Alan R.
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023/12/1
Y1 - 2023/12/1
N2 - For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this article, we consider the problem of few-shot incremental learning (FSIL), in which an AI agent is required to learn incrementally from a few data samples without forgetting the data it has previously learned. To solve this problem, we present a novel framework inspired by theories of concept learning in the hippocampus and the neocortex. Our framework represents object classes in the form of sets of clusters and stores them in memory. The framework replays data generated by the clusters of the old classes, to avoid forgetting when learning new classes. Our approach is evaluated on two object classification data sets resulting in state-of-the-art (SOTA) performance for class-incremental learning and FSIL. We also evaluate our framework for FSIL on a robot demonstrating that the robot can continually learn to classify a large set of household objects with limited human assistance.
AB - For most real-world applications, robots need to adapt and learn continually with limited data in their environments. In this article, we consider the problem of few-shot incremental learning (FSIL), in which an AI agent is required to learn incrementally from a few data samples without forgetting the data it has previously learned. To solve this problem, we present a novel framework inspired by theories of concept learning in the hippocampus and the neocortex. Our framework represents object classes in the form of sets of clusters and stores them in memory. The framework replays data generated by the clusters of the old classes, to avoid forgetting when learning new classes. Our approach is evaluated on two object classification data sets resulting in state-of-the-art (SOTA) performance for class-incremental learning and FSIL. We also evaluate our framework for FSIL on a robot demonstrating that the robot can continually learn to classify a large set of household objects with limited human assistance.
UR - http://www.scopus.com/inward/record.url?scp=85165679794&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85165679794&partnerID=8YFLogxK
U2 - 10.1109/TCDS.2023.3299755
DO - 10.1109/TCDS.2023.3299755
M3 - Article
AN - SCOPUS:85165679794
SN - 2379-8920
VL - 15
SP - 2004
EP - 2013
JO - IEEE Transactions on Cognitive and Developmental Systems
JF - IEEE Transactions on Cognitive and Developmental Systems
IS - 4
ER -