Principles of Neuromorphic Photonics

  title={Principles of Neuromorphic Photonics},
  author={Bhavin J. Shastri and Alexander N. Tait and Thomas Ferreira de Lima and Mitchell A. Nahmias and Hsuan-Tung Peng and Paul R. Prucnal},
In an age overrun with information, the ability to process reams of data has become crucial. [] Key Result We conclude with a future outlook of neuro-inspired photonic processing.
Analog Programmable-Photonic Computation
In this work, the foundations of a new computation theory are presented, explicitly designed to unleash the full potential of PIP, which enables overcoming some of the basic theoretical and technological limitations of existing computational models, can be implemented in other technologies and exhibits the potential to spark a ground-breaking impact on information society.
Deep Neural Network Through an InP SOA-Based Photonic Integrated Cross-Connect
A comprehensive analysis of the error evolution in the system reveals that the electrical/optical conversions dominate the error contribution, which suggests that an all optical approach is preferable for future neuromorphic computing hardware design.
The physical structure and operational details of a microring resonator-based Half-Adder (HA) circuit are studied and the conditions under which the performance and accuracy of information processing is compromised due to its physical limitations are outlined.
All-Optical Spiking Neuron Based on Passive Microresonator
It is demonstrated that the microresonator-based neuron can exhibit the typical characteristics of spiking neurons: excitability threshold, leaky integrating dynamics, refractory period, cascadability and inhibitory spiking behavior, paving the way to realize all-optical spiking neural networks.
A Survey on Silicon Photonics for Deep Learning
The landscape of silicon photonics to accelerate deep learning is surveyed, with a coverage of developments across design abstractions in a bottom-up manner, to convey both the capabilities and limitations of the silicon Photonics paradigm in the context of deep learning acceleration.
All-optical nonlinear activation function for photonic neural networks [Invited]
This work discusses two independent approaches of implementing the optical perceptrons nonlinear activation function based on nanophotonic structures exhibiting i) induced transparency and ii) reverse saturated absorption and shows that the all-optical nonlinearity provides about 3 and 7 dB extinction ratio for the two systems considered, respectively.
InP Photonic Integrated Multi-Layer Neural Networks: Architecture and Performance Analysis
We demonstrate the use of a wavelength converter, based on cross-gain modulation in a semiconductor optical amplifier (SOA), as a nonlinear function co-integrated within an all-optical neuron
Toward Neuromorphic Photonic Networks of Ultrafast Spiking Laser Neurons
This work introduces the recent and ongoing activities demonstrating controllable excitation of spiking signals in optical neurons based upon vertical-cavity surface emitting lasers (VCSEL-Neurons), and reports on ultrafast artificial laser neurons and their potentials for future neuromorphic (brainlike) photonic information processing systems.
Recent progress of integrated circuits and optoelectronic chips
The main contents include the development law of IC and optoelectronic chip technology, the IC design and processing technology, emerging memory and chip architecture, brain-like chip structure and its mechanism, heterogeneous integration, quantum chip technology and silicon photonics chip technology.
Energy Efficiency of Microring Resonator (MRR)-Based Binary Decision Diagram (BDD) Circuits
This work designs a microring resonator (MRR) based Binary Decision Diagram (BDD) NAND logic gate and study its characteristics inline with a MRR-based BDD half adder circuit proposed by Wada et.


Progress in neuromorphic photonics
The challenges and design rules for optoelectronic instantiation of artificial neurons are presented, and the proposed photonic architecture revolves around the processing network node composed of two parts: a nonlinear element and a network interface.
Experimental demonstration of reservoir computing on a silicon photonics chip.
This work proposes the first integrated passive silicon photonics reservoir and demonstrates that this generic chip can be used to perform arbitrary Boolean logic operations with memory as well as 5-bit header recognition up to 12.5 Gbit s(-1), without power consumption in the reservoir.
Photonic Neuromorphic Signal Processing and Computing
There has been a recent explosion of interest in spiking neural networks (SNNs), which code information as spikes or events in time. Spike encoding is widely accepted as the information medium
Recent progress in semiconductor excitable lasers for photonic spike processing
Recently, there has been tremendous interest in excitable optoelectronic devices and in particular excitable semiconductor lasers that could potentially enable unconventional processing approaches
Superconducting optoelectronic circuits for neuromorphic computing
A hybrid semiconductor-superconductor hardware platform for the implementation of neural networks and large-scale neuromorphic computing that could scale to systems with massive interconnectivity and complexity for advanced computing as well as explorations of information processing capacity in systems with an enormous number of information-bearing microstates.
Optical Logic-in the Light of Computer Technology
An examination of current technology illuminates the barriers that new digital logic technologies must overcome.
Silicon CMOS-integrated nano-photonics for computer and data communications beyond 100G
  • Y. Vlasov
  • Physics
    IEEE Communications Magazine
  • 2012
It is shown that the new emerging large-volume markets loosely defined as Computercom will demand new standards and new technologies, and how the balance between single-channel bit rate, and number of wavelengthmultiplexed and spatially multiplexed optical channels can help to satisfy the need for huge total bandwidth, while keeping cost low and power efficiency high.
A Novel Approach to Photonic Packaging Leveraging Existing High-Throughput Microelectronic Facilities
Two approaches to fiber-to-chip interfacing and one to hybrid photonic integration involving direct flip-chip assembly of photonic dies are demonstrated, meant to be universal by simultaneously allowing wide spectral bandwidth for coarse wavelength division multiplexing and large optical-port count.
Excitable laser processing network node in hybrid silicon: analysis and simulation.
This work presents a physically realistic optoelectronic simulation model of a circuit for dynamical laser neural networks and describes the physics, dynamics, and parasitics of one network node, which includes a bank of filters, a photodetector, and excitable laser.
Rationale and challenges for optical interconnects to electronic chips
The various arguments for introducing optical interconnections to silicon CMOS chips are summarized, and the challenges for optical, optoelectronic, and integration technologies are discussed. Optics