Dynamic neural network with memristive CIM and CAM for 2D and 3D vision
This work addresses the inefficiency and lack of dynamic association in AI models for vision applications, though it appears incremental as it builds on existing neural network architectures with hardware enhancements.
The authors tackled the problem of static AI models by proposing a hardware-software co-design using memristor-based dynamic neural networks for 2D and 3D vision tasks, achieving accuracy on par with software while reducing computational budget by up to 48.1% and energy consumption by up to 93.3%.
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.