Layer ensemble averaging for fault tolerance in memristive neural networks
Osama Yousuf, Brian D. Hoskins, K Ramu, Mitchell Fream, William A. Borders, Advait Madhavan, Matthew W. Daniels, Andrew Dienstfrey, Jabez J. McClelland, Martin Lueker-Boden, Gina C. Adam
Abstract
Artificial neural networks have advanced due to scaling dimensions, but conventional computing struggles with inefficiencies due to memory bottlenecks. In-memory computing architectures using memristor devices offer promise but face challenges due to hardware non-idealities. This work proposes layer ensemble averaging—a hardware-oriented fault tolerance scheme for improving inference performance of non-ideal memristive neural networks programmed with pre-trained solutions. Simulations on an image classification task and hardware experiments on a continual learning problem with a custom 20,000-device prototyping platform show significant performance gains, outperforming prior methods at similar redundancy levels and overheads. For the image classification task with 20% stuck-at faults, accuracy improves from 40% to 89.6% (within 5% of baseline), and for the continual learning problem, accuracy improves from 55% to 71% (within 1% of baseline). The proposed scheme is broadly applicable to accelerators based on a variety of different non-volatile device technologies. Fault tolerance is essential for reliable AI acceleration using novel memristive hardware. Yousuf et al. developed a training-free fault tolerance scheme and demonstrated on a 20,000-memristor prototyping platform that it outperforms other solutions.