ORCID Profile
0000-0002-7175-0285
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: AIP Publishing
Date: 11-2021
DOI: 10.1063/5.0062686
Abstract: In this article, the standard theoretical model accounting for a double barrier quantum well resonant tunneling diode (RTD) connected to a direct current source of voltage is simplified by representing its current–voltage characteristic with an analytically approachable, anti-symmetric N-shaped function. The time and variables involved are also transformed to reduce the number of parameters in the model. Responses observed in previous, more physically accurate studies are reproduced, including slow–fast dynamics, excitability, and bistability, relevant for spiking signal processing. A simple expression for the refractory time of the excitable response is derived and shown to be in good agreement with numerical simulations. In particular, the refractory time is found to be directly proportional to the circuit’s intrinsic inductance. The presence or absence of bistability in the dependence of the parameters is also discussed thoroughly. The results of this work can serve as a guideline in prospective endeavors to design and fabricate RTD-based neuromorphic circuits for power and time-efficient execution of neural network algorithms.
Publisher: American Physical Society (APS)
Date: 05-03-2021
Publisher: Optica Publishing Group
Date: 22-06-2022
DOI: 10.1364/OME.451706
Abstract: With the recent development of artificial intelligence and deep neural networks, alternatives to the Von Neumann architecture are in demand to run these algorithms efficiently in terms of speed, power and component size. In this theoretical study, a neuromorphic, optoelectronic nanopillar metal-cavity consisting of a resonant tunneling diode (RTD) and a nanolaser diode (LD) is demonstrated as an excitable pulse generator. With the proper configuration, the RTD behaves as an excitable system while the LD translates its electronic output into optical pulses, which can be interpreted as bits of information. The optical pulses are characterized in terms of their width, litude, response delay, distortion and jitter times. Finally, two RTD-LD units are integrated via a photodetector and their feasibility to generate and propagate optical pulses is demonstrated. Given its low energy consumption per pulse and high spiking rate, this device has potential applications as building blocks in neuromorphic processors and spiking neural networks.
Publisher: American Physical Society (APS)
Date: 25-02-2022
Publisher: IOP Publishing
Date: 14-07-2023
Abstract: Nanophotonic spiking neural networks (SNNs) based on neuron-like excitable subwavelength (submicrometre) devices are of key importance for realizing brain-inspired, power-efficient artificial intelligence (AI) systems with high degree of parallelism and energy efficiency. Despite significant advances in neuromorphic photonics, compact and efficient nanophotonic elements for spiking signal emission and detection, as required for spike-based computation, remain largely unexplored. In this invited perspective, we outline the main challenges, early achievements, and opportunities toward a key-enabling photonic neuro-architecture using III–V/Si integrated spiking nodes based on nanoscale resonant tunnelling diodes (nanoRTDs) with folded negative differential resistance. We utilize nanoRTDs as nonlinear artificial neurons capable of spiking at high-speeds. We discuss the prospects for monolithic integration of nanoRTDs with nanoscale light-emitting diodes and nanolaser diodes, and nanophotodetectors to realize neuron emitter and receiver spiking nodes, respectively. Such layout would have a small footprint, fast operation, and low power consumption, all key requirements for efficient nano-optoelectronic spiking operation. We discuss how silicon photonics interconnects, integrated photorefractive interconnects, and 3D waveguide polymeric interconnections can be used for interconnecting the emitter-receiver spiking photonic neural nodes. Finally, using numerical simulations of artificial neuron models, we present spike-based spatio-temporal learning methods for applications in relevant AI-based functional tasks, such as image pattern recognition, edge detection, and SNNs for inference and learning. Future developments in neuromorphic spiking photonic nanocircuits, as outlined here, will significantly boost the processing and transmission capabilities of next-generation nanophotonic spike-based neuromorphic architectures for energy-efficient AI applications. This perspective paper is a result of the European Union funded research project ChipAI in the frame of the Horizon 2020 Future and Emerging Technologies Open programme.
No related grants have been discovered for Juan Ignacio Ortega-Piwonka.