As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
In this paper, we propose an incremental neural network model for a general class of sequential multi-task classification problems where a training data of a task may not only have multiple class labels but also have task information. Such data property originates from the uncertainty of teaching signals given by a supervisor. To handle this type of classification problems, the proposed model consists of a three-layer feedforward neural network with long-term/short-term memories, and it has the following functions: one-pass incremental learning, task allocation, handling multi-label data, task consolidation, and knowledge transfer. We newly introduce the following two types of task consolidation functions other than the conventional error-based one: the task consolidation based on the co-occurrence relation of class labels and task information. In the experiments, we evaluate the proposed model for various kinds of data sets. The experimental results demonstrate that the proposed model has good performance in both classification and task categorization even if the task information is not always given.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.