连续推理：利用连续学习在神经符号 AI 中进行非单调推理（英文版）

英文标题：Continual Reasoning: Non-Monotonic Reasoning in Neurosymbolic AI using Continual Learning中文摘要：本文介绍一种称为连续推理的新方法，该方法将神经符号系统与知识和数据的循环学习相结合，以应对非单调推理任务，并在结果上显示了显著的改进。英文摘要：Despite the extensive investment and impressive recent progress at reasoningby similarity, deep learning continues to struggle with more complex forms ofreasoning such as non-monotonic and commonsense reasoning. Non-monotonicity isa property of non-classical reasoning typically seen in commonsense reasoning,whereby a reasoning