Abstract
Memristor-based neuromorphic systems have been proposed as a promising alternative to von Neumann computing architectures, which are currently challenged by the ever-increasing computational power required by modern artificial intelligence (AI) algorithms. The design and optimization of memristive devices for specific AI applications is thus of paramount importance, but still extremely complex, as many different physical mechanisms and their interactions have to be accounted for, which are, in many cases, not fully understood. The high complexity of the physical mechanisms involved and their partial comprehension are currently hampering the development of memristive devices and preventing their optimization. In this work, we tackle the application-oriented optimization of Resistive Random-Access Memory (RRAM) devices using a multiscale modeling platform. The considered platform includes all the involved physical mechanisms (i.e., charge transport and trapping, and ion generation, diffusion, and recombination) and accounts for the 3D electric and temperature field in the device. Thanks to its multiscale nature, the modeling platform allows RRAM devices to be simulated and the microscopic physical mechanisms involved to be investigated, the device performance to be connected to the material’s microscopic properties and geometries, the device electrical characteristics to be predicted, the effect of the forming conditions (i.e., temperature, compliance current, and voltage stress) on the device’s performance and variability to be evaluated, the analog resistance switching to be optimized, and the device’s reliability and failure causes to be investigated. The discussion of the presented simulation results provides useful insights for supporting the application-oriented optimization of RRAM technology according to specific AI applications, for the implementation of either non-volatile memories, deep neural networks, or spiking neural networks.
Highlights
Artificial Neural Networks (ANNs) are possibly the most prominent computational model used in modern artificial intelligence (AI) applications
Memristor-based neuromorphic systems have been proposed as a promising alternative to von Neumann computing architectures, which are currently challenged by the ever-increasing computational power required by modern artificial intelligence (AI) algorithms
Multiscale modeling provides a powerful tool for accelerating the further development and optimization of Resistive Random-Access Memory (RRAM) technology, focusing on the specific application (i.e., non-volatile memories (NVMs), ANN, or Spiking Neural Networks (SNNs))
Summary
Artificial Neural Networks (ANNs) are possibly the most prominent computational model used in modern artificial intelligence (AI) applications. An ever-increasing effort has been devoted to the experimentation of different ANN architectures, which has led to the development of ANNs constituted by an extremely high number of neurons and layers [1,2], known as deep neural networks (DNNs). Thanks to their high flexibility and Materials 2019, 12, 3461; doi:10.3390/ma12213461 www.mdpi.com/journal/materials. In most practical applications, DNNs are implemented in software and executed on von Neumann computer architectures that have to provide (i) sufficient computational power for fast training and inference, and (ii) a sufficiently large and fast memory for storing all the artificial neuron weights and any partial result. The energy efficiency of training and inference must be considered
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
