AUTHOR=Shamsi Jafar , Avedillo María José , Linares-Barranco Bernabé , Serrano-Gotarredona Teresa 

TITLE=Hardware Implementation of Differential Oscillatory Neural Networks Using VO 2-Based Oscillators and Memristor-Bridge Circuits

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2021.674567

DOI=10.3389/fnins.2021.674567

ISSN=1662-453X

ABSTRACT=Oscillatory Neural Networks (ONNs) are currently arousing interest in the research community for their potential to implement very fast, ultra-low-power computing capabilities by exploiting specific emerging technologies. From the architectural point of view, ONNs are based on the synchronization of neurons in cognitive processing as occurs in the human brain. As emerging technologies, VO2 and memristive devices show promising potential for the efficient implementation of ONNs. Abundant literature is now becoming available pertaining to the study and building of ONNs based on VO2 devices and resistive coupling, such as memristors. One drawback of direct resistive coupling is that physical resistances cannot be negative, but from the architectural and computational perspective this is actually a powerful advantage when interconnecting weights in ONNs. Here we solve the problem by proposing a hardware implementation technique based on differential ONNs with VO2-based oscillators and memristor-bridge circuits. The oscillators provide differential outputs with in-phase and anti-phase signals. The memristor-bridge circuit is used as an adjustable coupling function that is compatible with differential structures and capable of providing both positive and negative weights. By combining differential oscillators and memristor-bridge circuits, we were able to propose the hardware of a fully connected differential ONN and use it as an associative memory. The standard Hebbian rule was used for training, and the weights were mapped to the memristor-bridge circuit through a proposed mapping rule. The paper also introduces some functional and hardware specifications to evaluate the design. Evaluation showed that the retrieval accuracy of the proposed design is comparable to that of the classic Hopfield neural network.