使用自适应权重调制的高效无预演零遗忘持续学习
Efficient Rehearsal Free Zero Forgetting Continual Learning using Adaptive Weight Modulation
AI总结：
针对持续学习中的灾难性遗忘问题，本文提出一种通过为每个任务创建特定调制参数以实现零遗忘并最大化新任务性能的高效无预演方法。
摘要：
人工神经网络面临一个被称为持续学习的显著挑战，即在较长时间内获取多个任务的知识。由于先前学习的权重倾向于被调整以适应新任务的目标，导致了被称为灾难性遗忘的现象，从而产生了这一挑战。针对该问题的大多数方法试图在最大化新任务性能和最小化先前任务遗忘之间寻求平衡。相比之下，我们的方法试图在确保零遗忘的同时，最大化新任务的性能。这是通过为每个任务创建特定于任务的调制参数来实现的。在连续任务的学习过程中，只有这些参数是可学习参数。通过全面的实验评估，我们的模型在获取和保留对其他多任务模型构成困难的新任务方面表现出卓越的性能。这强调了我们的方法在防止灾难性遗忘的同时兼顾新任务获取的有效性。
英文摘要：
Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to be adjusted to suit the objectives of new tasks, resulting in a phenomenon called catastrophic forgetting. Most approaches to this problem seek a balance between maximizing performance on the new tasks and minimizing the forgetting of previous tasks. In contrast, our approach attempts to maximize the performance of the new task, while ensuring zero forgetting. This is accomplished by creating a task-specific modulation parameters for each task. Only these would be learnable parameters during learning of consecutive tasks. Through comprehensive experimental evaluations, our model demonstrates superior performance in acquiring and retaining novel tasks that pose difficulties for other multi-task models. This emphasizes the efficacy of our approach in preventing catastrophic forgetting while accommodating the acquisition of new tasks
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
