A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems

详细信息    查看全文

• 作者：Alexander Gepperth ; Cem Karaoguz
• 关键词：Perceptual learning ; Self ; organization ; Incremental learning ; Biological modeling
• 刊名：Cognitive Computation
• 出版年：2016
• 出版时间：October 2016
• 年：2016
• 卷：8
• 期：5
• 页码：924-934
• 全文大小：1,829 KB
• 刊物主题：Neurosciences; Computation by Abstract Devices; Artificial Intelligence (incl. Robotics); Computational Biology/Bioinformatics;
• 出版者：Springer US
• ISSN：1866-9964
• 卷排序：8

文摘

We present a biologically inspired architecture for incremental learning that remains resource-efficient even in the face of very high data dimensionalities (>1000) that are typically associated with perceptual problems. In particular, we investigate how a new perceptual (object) class can be added to a trained architecture without retraining, while avoiding the well-known catastrophic forgetting effects typically associated with such scenarios. At the heart of the presented architecture lies a generative description of the perceptual space by a self-organized approach which at the same time approximates the neighborhood relations in this space on a two-dimensional plane. This approximation, which closely imitates the topographic organization of the visual cortex, allows an efficient local update rule for incremental learning even in the face of very high dimensionalities, which we demonstrate by tests on the well-known MNIST benchmark. We complement the model by adding a biologically plausible short-term memory system, allowing it to retain excellent classification accuracy even under incremental learning in progress. The short-term memory is additionally used to reinforce new data statistics by replaying previously stored samples during dedicated “sleep” phases.