Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Maps

arXiv:2402.12465v1 Announce Type: new
Abstract: An intelligent system capable of continual learning is one that can process and extract knowledge from potentially infinitely long streams of pattern vectors. The major challenge that makes crafting such a system difficult is known as catastrophic forgetting - an agent, such as one based on artificial neural networks (ANNs), struggles to retain previously acquired knowledge when learning from new samples. Furthermore, ensuring that knowledge is preserved for previous tasks becomes more challenging when input …

abstract agent arxiv catastrophic forgetting challenge continual cs.lg cs.ne extract free intelligent knowledge major maps neuro online learning process type unsupervised vectors