神经存储程序记忆
Neural Stored-program Memory
摘要:
由外部存储器驱动的神经网络模拟计算机行为。这些模型使用存储器为神经控制器存储数据,可以学习算法和其他复杂的任务。在本文中,我们介绍了一种新的存储器来存储控制器的权重,类似于现代计算机体系结构中的存储程序存储器。该模型被称为神经存储程序记忆,增强了当前的记忆增强神经网络,创建了可微分机器,可以通过时间切换程序,适应可变的上下文,从而类似于通用图灵机。大量的实验表明,由此产生的机器不仅在经典的算法问题中表现出色,而且在组合、连续、少样本学习和问答任务中也有潜力。
英文摘要:
Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern computer architectures. The proposed model, dubbed Neural Stored-program Memory, augments current memory-augmented neural networks, creating differentiable machines that can switch programs through time, adapt to variable contexts and thus resemble the Universal Turing Machine. A wide range of experiments demonstrate that the resulting machines not only excel in classical algorithmic problems, but also have potential for compositional, continual, few-shot learning and question-answering 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。