A life-long learning vector quantization approach for interactive learning of multiple categories

• Published in: Neural networks Vol. 28; pp. 90 - 105
• Main Authors: Kirstein, Stephan, Wersing, Heiko, Gross, Horst-Michael, Körner, Edgar
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.04.2012; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Category learning; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Data processing. List processing. Character string processing; Exact sciences and technology; Feature selection; Learning; Life-long learning; Longevity; Memory organisation. Data processing; Pattern recognition. Digital image processing. Computational geometry; Robotics - standards; Robotics - trends; Software; Vector quantization; Life-long learning; Feature selection; Vector quantization; Category learning; Cluster analysis; Forgetting; Computer vision; Real time; Long term; Robotics; Interactive system; Learning; Dimension reduction; Cognitive theory; Categorization; Artificial intelligence; Visual task
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2011.12.003

We present a new method capable of learning multiple categories in an interactive and life-long learning fashion to approach the “stability–plasticity dilemma”. The problem of incremental learning of multiple categories is still largely unsolved. This is especially true for the domain of cognitive robotics, requiring real-time and interactive learning. To achieve the life-long learning ability for a cognitive system, we propose a new learning vector quantization approach combined with a category-specific feature selection method to allow several metrical “views” on the representation space of each individual vector quantization node. These category-specific features are incrementally collected during the learning process, so that a balance between the correction of wrong representations and the stability of acquired knowledge is achieved. We demonstrate our approach for a difficult visual categorization task, where the learning is applied for several complex-shaped objects rotated in depth.