Answers are grounded in this paper and cite their sources.
Oscillatory neural networks (ONNs), based on the thalamocortical neural system, use the phase dynamics of oscillator neurons to solve NP-hard problems-a key challenge for von-Neumann computing. For hardware realization of ONN, a scalable and low-power oscillator neuron is essential. Recently, a transient Joule heating induced high-nonlinearity in the I-V characteristics was demonstrated in area-scalable PrMnO3(PMO)-based RRAM. The extraordinarily high thermal resistivity of PMO (300× of Si) enables thermal runaway at lower power densities. In this letter, utilizing this highly non-linear and hysteretic I-V, we propose an oscillator neuron consisting of PMO device put in series with a resistor and a capacitor to produce self-sustained oscillations. The area scalable, sub-3 V operation, large output swing, along with the availability of synapse in the same material system makes the PMO-based oscillator attractive for ONN. A behavioral model of the oscillator is also developed in Verilog-A to explore the design space over which the device operates. Based on such experimentally calibrated circuit models, a large network of oscillators can be designed, and the performance can be evaluated for solving complex real-life applications.
No takes yet. Share an insight, caveat, or question.
Lashkare et al. (2018) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: