A Novel Computing Paradigm for MobileNetV3 using Memristor

The advancement in the field of machine learning is inextricably linked with the concurrent progress in domain-specific hardware accelerators such as GPUs and TPUs. However, the rapidly growing computational demands necessitated by larger models and increased data have become a primary bottleneck in further advancing machine learning, especially in mobile and edge devices. Currently, the neuromorphic computing paradigm based on memristors presents a promising solution. In this study, we introduce a memristor-based MobileNetV3 neural network computing paradigm and provide an end-to-end framework for validation. The results demonstrate that this computing paradigm achieves over 90% accuracy on the CIFAR10 dataset while saving inference time and reducing energy consumption. With the successful development and verification of MobileNetV3, the potential for realizing more memristor-based neural networks using this computing paradigm and open-source framework has significantly increased. This progress sets a groundbreaking pathway for future deployment initiatives. Recommended citation:

@INPROCEEDINGS{11228482, author={Li, Jiale and Liu, Zhihang and Ma, Sean Longyu and Sham, Chiu-Wing and Fu, Chong}, booktitle={2025 International Joint Conference on Neural Networks (IJCNN)}, title={A Novel Computing Paradigm for MobileNetV3 using Memristor}, year={2025}, volume={}, number={}, pages={1-8}, keywords={Energy consumption;Accuracy;Neuromorphic engineering;Computational modeling;Neural networks;Memristors;Graphics processing units;Machine learning;Data models;Hardware acceleration;Memristors-based neural networks;MobileNetV3;Neuromorphic computing}, doi={10.1109/IJCNN64981.2025.11228482}}