Traditional neural networks require enormous amounts of data to build their complex mappings during a slow training procedure that hinders their abilities for relearning and adapting to new data. Memory-augmented neural networks enhance neural networks with an explicit memory to overcome these issues. Access to this explicit memory, however, occurs via soft read and write operations involving every individual memory entry, resulting in a bottleneck when implemented using the conventional von Neumann computer architecture. To overcome this bottleneck, we propose a robust architecture that employs a computational memory unit as the explicit memory performing analog in-memory computation on high-dimensional vectors, while closely matching 32-bit software-equivalent accuracy. This is enabled by a content-based attention mechanism that represents unrelated items in the computational memory with uncorrelated high-dimensional vectors, whose real-valued components can be readily approximated by binary, or bipolar components. Experimental results demonstrate the efficacy of our approach on few-shot image classification tasks on the Omniglot dataset using more than 256,000 phase-change memory devices.

中文翻译：

---

健壮的高维记忆增强神经网络

传统的神经网络在缓慢的训练过程中需要大量数据来构建复杂的映射，这阻碍了它们重新学习和适应新数据的能力。记忆增强神经网络通过显式记忆增强神经网络以克服这些问题。然而，对这种显式内存的访问是通过涉及每个单独内存条目的软读写操作发生的，当使用传统的冯诺依曼计算机体系结构实现时，会导致瓶颈。为了克服这个瓶颈，我们提出了一种强大的架构，该架构采用计算内存单元作为显式内存，对高维向量执行模拟内存计算，同时与 32 位软件等效精度密切匹配。这是通过基于内容的注意力机制实现的，该机制用不相关的高维向量表示计算内存中的不相关项，其实值分量可以很容易地用二进制或双极分量近似。实验结果证明了我们的方法在使用超过 256,000 个相变存储设备的 Omniglot 数据集上的小样本图像分类任务上的有效性。