Benchmarking Inference Performance of Deep Learning Models on Analog Devices

Abstract

Analog hardware implemented deep learning models are promising for computation and energy constrained systems such as edge computing devices. However, the analog nature of the device and the associated many noise sources will cause changes to the value of the weights in the trained deep learning models deployed on such devices. In this study, systematic evaluation of the inference performance of trained popular deep learning models for image classification deployed on analog devices has been carried out, where additive white Gaussian noise has been added to the weights of the trained models during inference. It is observed that deeper models and models with more redundancy in design such as VGG are more robust to the noise in general. However, the performance is also affected by the design philosophy of the model, the detailed structure of the model, the exact machine learning task, as well as the datasets.

References in corpus (7)

• Deep Residual Learning for Image Recognition
• Deep Learning with Coherent Nanophotonic Circuits
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Deep Learning is Robust to Massive Label Noise
• Multiscale Co-Design Analysis of Energy, Latency, Area, and Accuracy of a ReRAM Analog Neural Training Accelerator
• Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation
• Noisy Computations during Inference: Harmful or Helpful?