A biologically motivated visual memory architecture for online learning of objects

We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that implements short-term and long-term memory for objects. A particular focus is the functional realization of online and incremental learning for the task of appearance-based object recognition of many complex-shaped objects. We propose some modifications of learning vector quantization algorithms that are especially adapted to the task of incremental learning and capable of dealing with the stabilityplasticity dilemma of such learning algorithms. Our technical implementation of the neural architecture is capable of online learning of 50 objects within less than three hours. c 2007 Elsevier Ltd. All rights reserved.

• Type: Journal
• Year: 2008
• Where: NN
• Authors: Stephan Kirstein, Heiko Wersing, Edgar Körner
• Keywords: Hierarchical Feature-detection Model, Incremental Learning, Neural Networks, NN 2008, Object Recognition