Uncertainty Modeling of Emerging Device-based Computing-in-Memory Neural Accelerators with Application to Neural Architecture Search
This work addresses the reliability problem for deploying neural networks on energy-efficient hardware, but it is incremental as it builds on existing neural architecture search methods.
The paper tackles the accuracy drop in deep neural networks when deployed on emerging computing-in-memory devices due to device uncertainties, proposing an uncertainty-aware neural architecture search scheme to identify models that are both accurate and robust, achieving a 5% improvement in accuracy under uncertainty compared to baseline models.
Emerging device-based Computing-in-memory (CiM) has been proved to be a promising candidate for high-energy efficiency deep neural network (DNN) computations. However, most emerging devices suffer uncertainty issues, resulting in a difference between actual data stored and the weight value it is designed to be. This leads to an accuracy drop from trained models to actually deployed platforms. In this work, we offer a thorough analysis of the effect of such uncertainties-induced changes in DNN models. To reduce the impact of device uncertainties, we propose UAE, an uncertainty-aware Neural Architecture Search scheme to identify a DNN model that is both accurate and robust against device uncertainties.