scholarly journals NanoLEDs for energy-efficient and gigahertz-speed spike-based sub-λ neuromorphic nanophotonic computing

Nanophotonics ◽  
2020 ◽  
Vol 9 (13) ◽  
pp. 4149-4162 ◽  
Author(s):  
Bruno Romeira ◽  
José M. L. Figueiredo ◽  
Julien Javaloyes
Keyword(s):  
Neural Networks ◽  
Energy Efficient ◽  
High Speed ◽  
Dynamic Properties ◽  
Optical Computing ◽  
Differential Conductance ◽  
Rate Equations ◽  
Dynamical Equations ◽  
Electrical Modulation ◽  
High Bandwidth

AbstractEvent-activated biological-inspired subwavelength (sub-λ) photonic neural networks are of key importance for future energy-efficient and high-bandwidth artificial intelligence systems. However, a miniaturized light-emitting nanosource for spike-based operation of interest for neuromorphic optical computing is still lacking. In this work, we propose and theoretically analyze a novel nanoscale nanophotonic neuron circuit. It is formed by a quantum resonant tunneling (QRT) nanostructure monolithic integrated into a sub-λ metal-cavity nanolight-emitting diode (nanoLED). The resulting optical nanosource displays a negative differential conductance which controls the all-or-nothing optical spiking response of the nanoLED. Here we demonstrate efficient activation of the spiking response via high-speed nonlinear electrical modulation of the nanoLED. A model that combines the dynamical equations of the circuit which considers the nonlinear voltage-controlled current characteristic, and rate equations that takes into account the Purcell enhancement of the spontaneous emission, is used to provide a theoretical framework to investigate the optical spiking dynamic properties of the neuromorphic nanoLED. We show inhibitory- and excitatory-like optical spikes at multi-gigahertz speeds can be achieved upon receiving exceptionally low (sub-10 mV) synaptic-like electrical activation signals, lower than biological voltages of 100 mV, and with remarkably low energy consumption, in the range of 10–100 fJ per emitted spike. Importantly, the energy per spike is roughly constant and almost independent of the incoming modulating frequency signal, which is markedly different from conventional current modulation schemes. This method of spike generation in neuromorphic nanoLED devices paves the way for sub-λ incoherent neural elements for fast and efficient asynchronous neural computation in photonic spiking neural networks.

Energy Efficient Superconducting Neural Networks for High-Speed Intellectual Data Processing Systems

2018 ◽  
Vol 28 (7) ◽  
pp. 1-6 ◽  
Author(s):  
Nikolay V. Klenov ◽  
Andrey E. Schegolev ◽  
Igor I. Soloviev ◽  
Sergey V. Bakurskiy ◽  
Maxim V. Tereshonok
Keyword(s):  
Neural Networks ◽  
Data Processing ◽  
Energy Efficient ◽  
High Speed

scholarly journals Implementation of Pruned Backpropagation Neural Network Based on Photonic Integrated Circuits

Photonics ◽  
2021 ◽  
Vol 8 (9) ◽  
pp. 363
Author(s):  
Qi Zhang ◽  
Zhuangzhuang Xing ◽  
Duan Huang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Integrated Circuits ◽  
Energy Efficient ◽  
High Speed ◽  
Large Scale ◽  
Matrix Operation ◽  
Optical Neural Networks ◽  
Optical Neural Network ◽  
Random Initialization

We demonstrate a pruned high-speed and energy-efficient optical backpropagation (BP) neural network. The micro-ring resonator (MRR) banks, as the core of the weight matrix operation, are used for large-scale weighted summation. We find that tuning a pruned MRR weight banks model gives an equivalent performance in training with the model of random initialization. Results show that the overall accuracy of the optical neural network on the MNIST dataset is 93.49% after pruning six-layer MRR weight banks on the condition of low insertion loss. This work is scalable to much more complex networks, such as convolutional neural networks and recurrent neural networks, and provides a potential guide for truly large-scale optical neural networks.

An Ultrawideband Microfabricated Gold-Based Antenna Array for Terahertz Communications

2020 ◽  
Author(s):  
Abdoalbaset Abohmra ◽  
Hasan Abbas ◽  
Jalil Kazim ◽  
Muhammad Rabbani ◽  
Chong Li ◽  
...  
Keyword(s):  
Communication Networks ◽  
Energy Efficient ◽  
High Speed ◽  
Coplanar Waveguide ◽  
Microwave Frequency ◽  
Future Generation ◽  
Data Rates ◽  
Terahertz Communications ◽  
High Bandwidth ◽  
The Cost

Abstract The microwave frequency band typically used for wireless communications will soon become saturated and will no longer be able to fulfil the high bandwidth demands of modern communication networks. Terahertz (THz) communication has appeared as a highly attractive, future-generation wireless technology that offers higher spectral bandwidth and, therefore, higher data rates. However, the full exploitation of THz technologies is contingent upon the availability of energy-efficient sources and devices. In this article, we presented a fabrication and measurement of microscale planar inverted cone antenna (PICA) array made of gold. Using an ungrounded coplanar waveguide feed, the microfabricated structure provides a bandwidth of 37.9 % with the resonant frequency of 0.925 THz. Given the cost of microfabrication is reducing substantially with rapid technological advancements, the results of this paper suggest that high-speed THz communications can be realised for widescale applications.

Energy efficient biomorphic pulse information coding in electronic neurons for the entrance unit of the neuroprocessor

2019 ◽  
Vol 5 (3) ◽  
pp. 186-212 ◽  
Author(s):  
Alexander D. Pisarev
Keyword(s):  
Neural Networks ◽  
Energy Efficiency ◽  
Energy Efficient ◽  
Information Transfer ◽  
Biological Systems ◽  
Technological Parameters ◽  
Input Unit ◽  
Efficient Operation ◽  
Electric Circuits ◽  
Electronic Neuron

This article studies the implementation of some well-known principles of information work of biological systems in the input unit of the neuroprocessor, including spike coding of information used in models of neural networks of the latest generation.<br> The development of modern neural network IT gives rise to a number of urgent tasks at the junction of several scientific disciplines. One of them is to create a hardware platform&nbsp;— a neuroprocessor for energy-efficient operation of neural networks. Recently, the development of nanotechnology of the main units of the neuroprocessor relies on combined memristor super-large logical and storage matrices. The matrix topology is built on the principle of maximum integration of programmable links between nodes. This article describes a method for implementing biomorphic neural functionality based on programmable links of a highly integrated 3D logic matrix.<br> This paper focuses on the problem of achieving energy efficiency of the hardware used to model neural networks. The main part analyzes the known facts of the principles of information transfer and processing in biological systems from the point of view of their implementation in the input unit of the neuroprocessor. The author deals with the scheme of an electronic neuron implemented based on elements of a 3D logical matrix. A pulsed method of encoding input information is presented, which most realistically reflects the principle of operation of a sensory biological neural system. The model of an electronic neuron for selecting ranges of technological parameters in a real 3D logic matrix scheme is analyzed. The implementation of disjunctively normal forms is shown, using the logic function in the input unit of a neuroprocessor as an example. The results of modeling fragments of electric circuits with memristors of a 3D logical matrix in programming mode are presented.<br> The author concludes that biomorphic pulse coding of standard digital signals allows achieving a high degree of energy efficiency of the logic elements of the neuroprocessor by reducing the number of valve operations. Energy efficiency makes it possible to overcome the thermal limitation of the scalable technology of three-dimensional layout of elements in memristor crossbars.

scholarly journals Dual-shot dynamics and ultimate frequency of all-optical magnetic recording on GdFeCo

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Sicong Wang ◽  
Chen Wei ◽  
Yuanhua Feng ◽  
Hongkun Cao ◽  
Wenzhe Li ◽  
...  
Keyword(s):  
Magnetization Reversal ◽  
Energy Efficient ◽  
High Speed ◽  
Data Transfer ◽  
Laser Pulses ◽  
Time Resolved ◽  
All Optical ◽  
Fs Laser ◽  
High Speed Data ◽  
Natural Way

AbstractAlthough photonics presents the fastest and most energy-efficient method of data transfer, magnetism still offers the cheapest and most natural way to store data. The ultrafast and energy-efficient optical control of magnetism is presently a missing technological link that prevents us from reaching the next evolution in information processing. The discovery of all-optical magnetization reversal in GdFeCo with the help of 100 fs laser pulses has further aroused intense interest in this compelling problem. Although the applicability of this approach to high-speed data processing depends vitally on the maximum repetition rate of the switching, the latter remains virtually unknown. Here we experimentally unveil the ultimate frequency of repetitive all-optical magnetization reversal through time-resolved studies of the dual-shot magnetization dynamics in Gd27Fe63.87Co9.13. Varying the intensities of the shots and the shot-to-shot separation, we reveal the conditions for ultrafast writing and the fastest possible restoration of magnetic bits. It is shown that although magnetic writing launched by the first shot is completed after 100 ps, a reliable rewriting of the bit by the second shot requires separating the shots by at least 300 ps. Using two shots partially overlapping in space and minimally separated by 300 ps, we demonstrate an approach for GHz magnetic writing that can be scaled down to sizes below the diffraction limit.

scholarly journals Integrated photonic FFT for photonic tensor operations towards efficient and high-speed neural networks

Nanophotonics ◽  
2020 ◽  
Vol 9 (13) ◽  
pp. 4097-4108 ◽  
Author(s):  
Moustafa Ahmed ◽  
Yas Al-Hadeethi ◽  
Ahmed Bakry ◽  
Hamed Dalir ◽  
Volker J. Sorger
Keyword(s):  
Neural Networks ◽  
Graphics Processing Units ◽  
High Speed ◽  
Fourier Transforms ◽  
Optoelectronic Device ◽  
Small Sample ◽  
Sample Number ◽  
Chip Area ◽  
Domain Specific ◽  
Graphics Processing

AbstractThe technologically-relevant task of feature extraction from data performed in deep-learning systems is routinely accomplished as repeated fast Fourier transforms (FFT) electronically in prevalent domain-specific architectures such as in graphics processing units (GPU). However, electronics systems are limited with respect to power dissipation and delay, due to wire-charging challenges related to interconnect capacitance. Here we present a silicon photonics-based architecture for convolutional neural networks that harnesses the phase property of light to perform FFTs efficiently by executing the convolution as a multiplication in the Fourier-domain. The algorithmic executing time is determined by the time-of-flight of the signal through this photonic reconfigurable passive FFT ‘filter’ circuit and is on the order of 10’s of picosecond short. A sensitivity analysis shows that this optical processor must be thermally phase stabilized corresponding to a few degrees. Furthermore, we find that for a small sample number, the obtainable number of convolutions per {time, power, and chip area) outperforms GPUs by about two orders of magnitude. Lastly, we show that, conceptually, the optical FFT and convolution-processing performance is indeed directly linked to optoelectronic device-level, and improvements in plasmonics, metamaterials or nanophotonics are fueling next generation densely interconnected intelligent photonic circuits with relevance for edge-computing 5G networks by processing tensor operations optically.

scholarly journals Hybrid Mamdani Fuzzy Rules and Convolutional Neural Networks for Analysis and Identification of Animal Images

Computation ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 35
Author(s):  
Hind R. Mohammed ◽  
Zahir M. Hussain
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
High Speed ◽  
Moving Objects ◽  
Real Life ◽  
Fuzzy Rules ◽  
High Rate ◽  
Moving Images ◽  
Animal Images

Accurate, fast, and automatic detection and classification of animal images is challenging, but it is much needed for many real-life applications. This paper presents a hybrid model of Mamdani Type-2 fuzzy rules and convolutional neural networks (CNNs) applied to identify and distinguish various animals using different datasets consisting of about 27,307 images. The proposed system utilizes fuzzy rules to detect the image and then apply the CNN model for the object’s predicate category. The CNN model was trained and tested based on more than 21,846 pictures of animals. The experiments’ results of the proposed method offered high speed and efficiency, which could be a prominent aspect in designing image-processing systems based on Type 2 fuzzy rules characterization for identifying fixed and moving images. The proposed fuzzy method obtained an accuracy rate for identifying and recognizing moving objects of 98% and a mean square error of 0.1183464 less than other studies. It also achieved a very high rate of correctly predicting malicious objects equal to recall = 0.98121 and a precision rate of 1. The test’s accuracy was evaluated using the F1 Score, which obtained a high percentage of 0.99052.

scholarly journals Fog Computing-Assisted Energy-Efficient Resource Allocation for High-Mobility MIMO-OFDMA Networks

2018 ◽  
Vol 2018 ◽  
pp. 1-8
Author(s):  
Lingyun Lu ◽  
Tian Wang ◽  
Wei Ni ◽  
Kai Li ◽  
Bo Gao
Keyword(s):  
Resource Allocation ◽  
Energy Efficient ◽  
High Speed ◽  
Optimization Problem ◽  
Fog Computing ◽  
High Mobility ◽  
High Speed Train ◽  
Efficient Resource ◽  
Energy Efficient Resource Allocation ◽  
System Configurations

This paper presents a suboptimal approach for resource allocation of massive MIMO-OFDMA systems for high-speed train (HST) applications. An optimization problem is formulated to alleviate the severe Doppler effect and maximize the energy efficiency (EE) of the system. We propose to decouple the problem between the allocations of antennas, subcarriers, and transmit powers and solve the problem by carrying out the allocations separately and iteratively in an alternating manner. Fast convergence can be achieved for the proposed approach within only several iterations. Simulation results show that the proposed algorithm is superior to existing techniques in terms of system EE and throughput in different system configurations of HST applications.

scholarly journals Programmable phase-change metasurfaces on waveguides for multimode photonic convolutional neural network

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Changming Wu ◽  
Heshan Yu ◽  
Seokhyeong Lee ◽  
Ruoming Peng ◽  
Ichiro Takeuchi ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Phase Change ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Phase Change Materials ◽  
Refractive Index Change ◽  
Optical Computing ◽  
Machine Learning Algorithms ◽  
Matrix Vector Multiplication

AbstractNeuromorphic photonics has recently emerged as a promising hardware accelerator, with significant potential speed and energy advantages over digital electronics for machine learning algorithms, such as neural networks of various types. Integrated photonic networks are particularly powerful in performing analog computing of matrix-vector multiplication (MVM) as they afford unparalleled speed and bandwidth density for data transmission. Incorporating nonvolatile phase-change materials in integrated photonic devices enables indispensable programming and in-memory computing capabilities for on-chip optical computing. Here, we demonstrate a multimode photonic computing core consisting of an array of programable mode converters based on on-waveguide metasurfaces made of phase-change materials. The programmable converters utilize the refractive index change of the phase-change material Ge2Sb2Te5 during phase transition to control the waveguide spatial modes with a very high precision of up to 64 levels in modal contrast. This contrast is used to represent the matrix elements, with 6-bit resolution and both positive and negative values, to perform MVM computation in neural network algorithms. We demonstrate a prototypical optical convolutional neural network that can perform image processing and recognition tasks with high accuracy. With a broad operation bandwidth and a compact device footprint, the demonstrated multimode photonic core is promising toward large-scale photonic neural networks with ultrahigh computation throughputs.

Sign in / Sign up

Export Citation Format

Share Document