Robust High-dimensional Memory-augmented Neural Networks
Geethan Karunaratne, Manuel Schmuck, Manuel Le Gallo, Giovanni, Cherubini, Luca Benini, Abu Sebastian, Abbas Rahimi

TL;DR
This paper introduces a robust high-dimensional memory-augmented neural network architecture that leverages analog in-memory computation with phase-change memory devices to improve efficiency and accuracy in few-shot image classification.
Contribution
It proposes a novel computational memory unit using high-dimensional vectors and content-based attention, enabling efficient analog in-memory computation with software-equivalent accuracy.
Findings
Effective on Omniglot few-shot classification tasks
Utilizes over 256,000 phase-change memory devices
Merges deep neural representations with high-dimensional computing
Abstract
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 (HD) vectors, while closely matching 32-bit software-equivalent accuracy. This is achieved by a content-based attention mechanism that represents unrelated items in the computational…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsContent-based Attention
