Artificial neural networks have advanced due to scaling dimensions, but
conventional computing faces inefficiency due to the von Neumann bottleneck.
In-memory computation architectures, like memristors, offer promise but face
challenges due to hardware non-idealities. This work proposes and
experimentally demonstrates layer ensemble averaging, a technique to map
pre-trained neural network solutions from software to defective hardware
crossbars of emerging memory devices and reliably attain near-software
performance on inference. The approach is investigated using a custom
20,000-device hardware prototyping platform on a continual learning problem
where a network must learn new tasks without catastrophically forgetting
previously learned information. Results demonstrate that by trading off the
number of devices required for layer mapping, layer ensemble averaging can
reliably boost defective memristive network performance up to the software
baseline. For the investigated problem, the average multi-task classification
accuracy improves from 61 % to 72 % (< 1 % of software baseline) using the
proposed approach.

这项研究提出并实验性地展示了一种层集成平均的技术，通过将预先训练的神经网络解决方案从软件映射到有缺陷的硬件交叉栅极存储器上，可可靠地达到接近软件性能的推理表现。研究结果表明，通过牺牲层映射所需的设备数量，层集成平均可以可靠地提升缺陷忆阻网络的性能，与软件基准相比，多任务分类准确率从 61% 提高到 72%（不到软件基准的 1%）。