Search for: All records

Artificial Intelligence (AI) is moving towards the edge. Training an AI model for edge computing on a centralized server increases latency, and the privacy of edge users is jeopardized due to private data transfer through a less secure communication channels. Additionally, existing high-power computing systems are battling with memory and data transfer bottlenecks between the processor and memory. Federated Learning (FL) is a collaborative AI learning paradigm for distributed local devices that operates without transferring local data. Local participant devices share the updated network parameters with the central server instead of sending the original data. The central server updates the global AI model and deploys the model to the local clients. As the local data resides only on the edge, these devices need to be protected from cyberattacks. The Federated Intrusion Detection System (FIDS) could be a viable system to protect edge devices as opposed to a centralized protection system. However, on-device training of the model in resource constrained devices may suffer from excessive power drain, in addition to memory and area overhead. In this work we present a memristor based system for AI training on edge devices. Memristor devices are ideal candidates for processing in memory, as their dynamic resistance properties allow them to perform multiply-add operations in parallel in the analog domain with extreme efficiency. Alternatively, existing CMOS-based PIM systems are typically developed for edge inference based on pretrained weights, and are not equipped for on-chip training. We show the effectiveness of the system, where successful learning and recognition is achieved completely within edge devices. The classification accuracy of the memristor system shows negligible loss when compared a software implementation. To the best of our knowledge, this first demonstration of a memristor based federated learning system. We demonstrate the effectiveness of this system as an intrusion detection platform for edge devices, although given the flexibility of the learning algorithm, it could be used to enhance many types of on board leaning and classification applications. 

Memristor devices fabricated using the chalcogenide Ge 2 Te 3 phase change thin films in a metal-insulator-metal structure are characterized using thermal and electrical stimuli in this study. Once the thermal and electrical stimuli are applied, cross-sectional transmission electron microscopy (TEM) and X-ray energy-dispersive spectroscopy (XEDS) analyses are performed to determine structural and compositional changes in the devices. Electrical measurements on these devices showed a need for increasing compliance current between cycles to initiate switching from low resistance state (LRS) to high resistance state (HRS). The measured resistance in HRS also exhibited a steady decrease with increase in the compliance current. High resolution TEM studies on devices in HRS showed the presence of residual crystalline phase at the top-electrode/dielectric interface, which may explain the observed dependence on compliance current. XEDS study revealed diffusion related processes at dielectric-electrode interface characterized, by the separation of Ge 2 Te 3 into Ge- and Te- enriched interfacial layers. This was also accompanied by spikes in O level at these regions. Furthermore, in-situ heating experiments on as-grown thin films revealed a deleterious effect of Ti adhesive layer, wherein the in-diffusion of Ti leads to further degradation of the dielectric layer. This experimental physics-based study shows that the large HRS/LRS ratio below the current compliance limit of 1 mA and the ability to control the HRS and LRS by varying the compliance current are attractive for memristor and neuromorphic computing applications.