Abstract
As a key building block of biological cortex, neurons are powerful information processing units and can achieve highly complex nonlinear computations even in individual cells. Hardware implementation of artificial neurons with similar capability is of great significance for the construction of intelligent, neuromorphic systems. Here, we demonstrate an artificial neuron based on NbOx volatile memristor that not only realizes traditional all-or-nothing, threshold-driven spiking and spatiotemporal integration, but also enables dynamic logic including XOR function that is not linearly separable and multiplicative gain modulation among different dendritic inputs, therefore surpassing neuronal functions described by a simple point neuron model. A monolithically integrated 4 × 4 fully memristive neural network consisting of volatile NbOx memristor based neurons and nonvolatile TaOx memristor based synapses in a single crossbar array is experimentally demonstrated, showing capability in pattern recognition through online learning using a simplified δ-rule and coincidence detection, which paves the way for bio-inspired intelligent systems.
Highlights
As a key building block of biological cortex, neurons are powerful information processing units and can achieve highly complex nonlinear computations even in individual cells
A monolithically integrated 4 × 4 spiking neural network consisting of volatile NbOx memristor-based neurons and nonvolatile TaOx memristor-based synapses in a single crossbar array is experimentally demonstrated, showing capability in performing pattern recognition through online learning based on a simplified δ-rule and achieving coincidence detection
We have demonstrated an artificial neuron based on threshold switching in NbOx devices, which displays four critical features: threshold-driven spiking, spatiotemporal integration, dynamic logic including XOR that is not linearly separable and gain modulation
Summary
As a key building block of biological cortex, neurons are powerful information processing units and can achieve highly complex nonlinear computations even in individual cells. Inspired by the structure and principles of the human brain, neuromorphic computing has great potential in the generation of computing technology, with massive parallelism and high efficiency, holding great prospect in overcoming the bottleneck of von Neumann architecture and extending the boundary of intelligence To achieve this goal, the development of highly compact artificial neurons and synapses, especially that capture important neuronal and synaptic dynamics, as well as the construction of hardware systems based on such artificial elements are of great significance. We report an artificial neuron based on NbOx volatile memristor that realizes all-or-nothing, threshold-driven spiking and spatiotemporal integration, and enables dynamic logic and gain modulation among different dendritic inputs, going beyond the functions of a simple point neuron model. The multiplicative gain modulation of the artificial neuron has been utilized to achieve receptive field remapping, which can potentially enhance the stability of artificial visual systems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
