Quantcast

Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization

Research paper by German I. Parisi, Jun Tani, Cornelius Weber, Stefan Wermter

Indexed on: 28 May '18Published on: 28 May '18Published in: arXiv - Computer Science - Artificial Intelligence



Abstract

Humans excel at continually acquiring and fine-tuning knowledge over sustained time spans. This ability, typically referred to as lifelong learning, is crucial for artificial agents interacting in real-world, dynamic environments where i) the number of tasks to be learned is not pre-defined, ii) training samples become progressively available over time, and iii) annotated samples may be very sparse. In this paper, we propose a dual-memory self-organizing system that learns spatiotemporal representations from videos. The architecture draws inspiration from the interplay of the hippocampal and neocortical systems in the mammalian brain argued to mediate the complementary tasks of quickly integrating specific experiences, i.e., episodic memory (EM), and slowly learning generalities from episodic events, i.e., semantic memory (SM). The complementary memories are modeled as recurrent self-organizing neural networks: The EM quickly adapts to incoming novel sensory observations via competitive Hebbian Learning, whereas the SM progressively learns compact representations by using task-relevant signals to regulate intrinsic levels of neurogenesis and neuroplasticity. For the consolidation of knowledge, trajectories of neural reactivations are periodically replayed to both networks. We analyze and evaluate the performance of our approach with the CORe50 benchmark dataset for continuous object recognition from videos. We show that the proposed approach significantly outperforms current (supervised) methods of lifelong learning in three different incremental learning scenarios, and that due to the unsupervised nature of neural network self-organization, our approach can be used in scenarios where sample annotations are sparse.