@phdthesis {phdthesisreference201009015231457413,
	title = {Interactive and life-long learning for identification and categorization tasks},
	author = {Stephan Kirstein},
	year = {2010},
	abstract = {The presented thesis focuses on life-long and interactive learning for identification and categorization tasks. The fundamental and still largely unsolved problem of life-long learning with artificial neural networks is the so-called {\textquotedblleft}stability-plasticity dilemma{\textquotedblright}. To achieve plasticity the learning approach must be able to continuously integrate newly acquired knowledge into its internal representation, while for the stability the conservation of this knowledge is required. To achieve interactive learning for difficult recognition problems the separation into an intermediate and fast learning short-term memory (STM) and a slower learning long-term memory (LTM) is proposed. For the incremental build up of the STM a similarity-based one-shot learning method was developed. Furthermore two different memory consolidation algorithms were proposed enabling the incremental learning of LTM representations for various identification and categorization tasks. For identification tasks different modifications to the Learning Vector Quantization (LVQ) network architecture are proposed. The major changes of the LVQ approach are an error-based node insertion rule and a node dependent learning rate. Both extensions enable incremental and life-long learning for identification problems. For life-long learning of categories this extended LVQ model was combined with a forward-feature selection method. This selection method incrementally extracts small sets of category-specific features and therefore allows for a compact representation of categories. In several interactive and offline recognition experiments the efficiency and performance of the proposed learning methods could be shown for difficult visual recognition problems. Additionally an active vision system was developed that utilizes the proposed learning methods. This integrated system enables learning of visual representations based on natural and complex-shaped objects presented in hand.},
	url = {http://www.db-thueringen.de/servlets/DocumentServlet?id=15700},
	institution = {Honda Research Institute / TU Ilmenau}
}