Dynamic neural network with memristive CIM and CAM for 2D and 3D vision

Autor:	Zhang, Yue, Zhang, Woyu, Wang, Shaocong, Lin, Ning, Yu, Yifei, He, Yangu, Wang, Bo, Jiang, Hao, Lin, Peng, Xu, Xiaoxin, Qi, Xiaojuan, Wang, Zhongrui, Zhang, Xumeng, Shang, Dashan, Liu, Qi, Cheng, Kwang-Ting, Liu, Ming
Rok vydání:	2024
Předmět:	Computer Science - Hardware Architecture Computer Science - Artificial Intelligence Computer Science - Emerging Technologies Computer Science - Neural and Evolutionary Computing
Druh dokumentu:	Working Paper
Popis:	The brain is dynamic, associative and efficient. It reconfigures by associating the inputs with past experiences, with fused memory and processing. In contrast, AI models are static, unable to associate inputs with past experiences, and run on digital computers with physically separated memory and processing. We propose a hardware-software co-design, a semantic memory-based dynamic neural network (DNN) using memristor. The network associates incoming data with the past experience stored as semantic vectors. The network and the semantic memory are physically implemented on noise-robust ternary memristor-based Computing-In-Memory (CIM) and Content-Addressable Memory (CAM) circuits, respectively. We validate our co-designs, using a 40nm memristor macro, on ResNet and PointNet++ for classifying images and 3D points from the MNIST and ModelNet datasets, which not only achieves accuracy on par with software but also a 48.1% and 15.9% reduction in computational budget. Moreover, it delivers a 77.6% and 93.3% reduction in energy consumption. Comment: In press
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.08990 Zobrazit plný text záznamu View this record from Arxiv