All-optical Neural Network Research Articles

Real-time target recognition with all-optical neural networks for ghost imaging.

The generation and structural characteristics of random speckle patterns impact the implementation and imaging quality of computational ghost imaging. Their modulation is limited by traditional electronic hardware. We aim to address this limitation using the features of an all-optical neural network. This work proposes a real-time target recognition system based on an all-optical diffraction deep neural network for ghost imaging. We use a trained neural network to perform pure phase modulation on visible light, and directly complete the target recognition task by detecting the maximum value of light intensity signals at different positions. We optimized the system by simulating the effects of parameters, such as the number of layers of the network, photosensitive pixel, unit area etc., on the final recognition performance, and the accuracy of target recognition reached 91.73%. The trained neural network is materialised by 3D printing technology and experiments confirmed that the system successfully performs real-time target recognition at a low sampling rate of 1.25%. It also verified the feasibility and noise resistance of the system in practical application scenarios.

Dynamically reconfigurable all-optical neural network based on a hybrid graphene metasurface array

In recent years, optical neural networks (ONNs) have received considerable attention for their intrinsic parallelism and low energy consumption, making them a vital area of research. However, the current passive diffractive ONNs lack dynamic tunability after fabrication for specific tasks. Here, we propose a dynamically reconfigurable diffractive deep neural network based on a hybrid graphene metasurface array, wherein the transmission and refractive index of each pixel can be finely adjusted via gate voltage. This capability enables the tailored modulation of the incident light’s amplitude and phase at each pixel, aligning with specific task requirements. The simulation results show the attainability of a dynamic modulation range of 7.97dB (ranging from −8.56dB to −0.591dB). Additionally, this proposed diffractive neural network platform incorporates an ultrathin structure comprising a one-atom-thick graphene layer and nanoscale metallic metastructures, rendering it compatible with complementary metal-oxide-semiconductor technology. Notably, a classification accuracy of 92.14% for a single-layer neural network operating in the terahertz spectrum is achieved based on the calculation result. This proposed platform presents compelling prospects for constructing various artificial neural network architectures with applications ranging from drug screening to automotive driving and vision sensing.

Optical authentication scheme based on all-optical neural network.

Diffractive deep neural network is architectural designs based on the principles of neural networks, which consists of multiple diffraction layers and has the remarkable ability to perform machine learning tasks at the speed of light. In this paper, a novel optical authentication system was presented that utilizes the diffractive deep neural network principle. By carefully manipulating a light beam with both a public key and a private key, we are able to generate a unique and secure image representation at a precise distance. The generated image can undergo authentication by being processed through the proposed authentication system. Leveraging the utilization of invisible terahertz light, the certification system possesses inherent characteristics of concealment and enhanced security. Additionally, the entire certification process operates solely through the manipulation of the light beam, eliminating the need for electronic calculations. As a result, the system offers rapid certification speed. The proposed optical authentication scheme is further validated through computer simulations, which showcase its robust security and high precision. This method holds immense potential for diverse applications in optical neural network authentication, warranting a broad scope of future prospects.

All-optical neural network nonlinear activation function based on the optical bistability within a micro-ring resonator

Training all-optical neural networks in itself remains an unresolved problem, and the challenges compound when the problem is turned into the hardware implementations. In this paper, we propose a nonlinear activation function based on optical bistability within a micro-ring resonator (MRR), achieving threshold control without external modulation. Furthermore, a convolutional neural network similar to the Le-Net-5 architecture is designed, in which all nonlinear activation functions are composed of optical bistable hysteresis loop. The numerical simulation results demonstrate that the recognition rate on the Fashion-MNIST dataset can achieve 91.3%, which means that the optical neuromorphic computation can be implemented by utilizing the nonlinear optical effects themselves in the all-optical hardware. Such a scheme promises access to the all-optical neural network training in the optical hardware environment compared to numerical activation functions.

Aided diagnosis of thyroid nodules based on an all-optical diffraction neural network.

Thyroid cancer is the most common malignancy in the endocrine system, with its early manifestation being the presence of thyroid nodules. With the advantages of convenience, noninvasiveness, and a lack of radiation, ultrasound is currently the first-line screening tool for the clinical diagnosis of thyroid nodules. The use of artificial intelligence to assist diagnosis is an emerging technology. This paper proposes the use optical neural networks for potential application in the auxiliary diagnosis of thyroid nodules. Ultrasound images obtained from January 2013 to December 2018 at the Institute and Hospital of Oncology, Tianjin Medical University, were included in a dataset. Patients who consecutively underwent thyroid ultrasound diagnosis and follow-up procedures were included. We developed an all-optical diffraction neural network to assist in the diagnosis of thyroid nodules. The network is composed of 5 diffraction layers and 1 detection plane. The input image is placed 10 mm away from the first diffraction layer. The input of the diffractive neural network is light at a wavelength of 632.8 nm, and the output of this network is determined by the amplitude and light intensity obtained from the detection region. The all-optical neural network was used to assist in the diagnosis of thyroid nodules. In the classification task of benign and malignant thyroid nodules, the accuracy of classification on the test set was 97.79%, with an area under the curve value of 99.8%. In the task of detecting thyroid nodules, we first trained the model to determine whether any nodules were present and achieved an accuracy of 84.92% on the test set. Our study demonstrates the potential of all-optical neural networks in the field of medical image processing. The performance of the models based on optical neural networks is comparable to other widely used network models in the field of image classification.

Time-stretch optical neural network with time-division multiplexing

As factors such as power consumption and bandwidth constrain the development of electronic computing in deep learning, optical neuromorphic computing has the potential to meet the growing computational demands of artificial intelligence, presenting various opportunities and challenges. In this paper, we propose an all-optical neural network through a combination of time-stretching and time-division multiplexing that can be used for the classification of multiple datasets. The system modulates a large number of parameters into chirp optical pulses by time-stretching and increases operational efficiency in conjunction with time-division multiplexing. This all-optical neural network system proposed is capable of operating at the speed of 1 Tera-OPS/s and can achieve data transfer rate in excess of 800 Gbit/s. The system is tested by the feedforward neural network, and the computational simulation realized very encouraging and considerable results.

An improved all-optical diffractive deep neural network with less parameters for gesture recognition

As a framework of optical machine learning, all-optical diffractive neural network (D2NN) has delivered an ideal outcome of feature detection and target classification, currently raising high interest in the optics and photonics community. In this paper, we applied an improved D2NN architecture to the field of gesture recognition, which features more complicated contour than the common MNIST handwriting recognition in the previous literature. The proposed network structure incorporates the wavelet-like phase modulation pattern technique and the highway network on the basis of all-optical neural network. Through modulating the phase of incident light, the wavelet-like pattern can substantially reduce the parameters in the network layer. In addition, a highway network is employed to address the vanishing gradient phenomenon in the training process. In the experiment, we numerically achieved blind testing accuracy of 95.6% for identifying ten different gestures, and the number of parameters is only 3% of the regular D2NN. Reliability test and analysis show that the proposed method is a high-efficiency solution with low-parameters expecting for implementation of various machine learning tasks.

On-chip ultra-compact nonvolatile photonic synapse

The important research content of modern communication systems is to realize high-speed, stable, and intelligent information transmission and processing. All-optical neural networks based on the silicon integrated technology and phase change materials (PCMs) can realize picosecond-level modulation speed, faster processing speed, and lower energy consumption compared with the traditional electrical communication system. The photonic synapse is the core component of the all-optical neural network module, but the existing photonic synapses based on PCMs require a modulation distance (MD) of several micrometers or even ten micrometers to achieve a large output intensity range. In this paper, we propose an ultra-compact nonvolatile photonic synapse, in which MD can be shortened to 1 μm, breaking the record of the minimum signal MD of the silicon photonic synapse using the PCMs. At the same time, the output intensity range of our synapse is almost twice that of the existing research. Based on this photonic synapse, we analyze the relationship between the output response and incident wavelength, which can help to design an ultra-compact photonic convolutional neural network. This work has great potential in future photonic computing and photonic communication technologies.

Nonlinear germanium-silicon photodiode for activation and monitoring in photonic neuromorphic networks

Silicon photonics is promising for artificial neural networks computing owing to its superior interconnect bandwidth, low energy consumption and scalable fabrication. However, the lack of silicon-integrated and monitorable optical neurons limits its revolution in large-scale artificial neural networks. Here, we highlight nonlinear germanium-silicon photodiodes to construct on-chip optical neurons and a self-monitored all-optical neural network. With specifically engineered optical-to-optical and optical-to-electrical responses, the proposed neuron merges the all-optical activation and non-intrusive monitoring functions in a compact footprint of 4.3 × 8 μm2. Experimentally, a scalable three-layer photonic neural network enables in situ training and learning in object classification and semantic segmentation tasks. The performance of this neuron implemented in a deep-scale neural network is further confirmed via handwriting recognition, achieving a high accuracy of 97.3%. We believe this work will enable future large-scale photonic intelligent processors with more functionalities but simplified architecture.

Emulation and modelling of semiconductor optical amplifier-based all-optical photonic integrated deep neural network with arbitrary depth

We experimentally demonstrate the emulation of scaling of the semiconductor optical amplifier (SOA) based integrated all-optical neural network in terms of number of input channels and layer cascade, with chromatic input at the neuron and monochromatic output conversion, obtained by exploiting cross-gain-modulation effect. We propose a noise model for investigating the signal degradation on the signal processing after cascades of SOAs, and we validate it via experimental results. Both experiments and simulations claim that the all-optical neuron (AON), with wavelength conversion as non-linear function, is able to compress noise for noisy optical inputs. This suggests that the use of SOA-based AON with wavelength conversion may allow for building neural networks with arbitrary depth. In fact, an arbitrarily deep neural network, built out of seven-channel input AONs, is shown to guarantee an error minor than 0.1 when operating at input power levels of −20 dBm/channel and with a 6 dB input dynamic range. Then the simulations results, extended to an arbitrary number of input channels and layers, suggest that by cascading and interconnecting multiple of these monolithically integrated AONs, it is possible to build a neural network with 12-inputs/neuron 12 neurons/layer and arbitrary depth scaling, or an 18-inputs/neuron 18-neurons/layer for single layer implementation, to maintain an output error <0.1. Further improvement in height scalability can be obtained by optimizing the input power.

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 realized with SOA and wavelength-division multiplexing technology. We investigate the impact of fully monolithically integrated linear and nonlinear functions on the all-optical neuron output with respect to the number of synapses/neuron and data rate. Results suggest that the number of inputs can scale up to 64 while guaranteeing a large input power dynamic range of 36 dB with neglectable error introduction. We also investigate the performance of its nonlinear transfer function by tuning the total input power and data rate: The monolithically integrated neuron performs about 10% better in accuracy than the corresponding hybrid device for the same data rate. These all-optical neurons are then used to simulate a 64:64:10 two-layer photonic deep neural network for handwritten digit classification, which shows an 89.5% best-case accuracy at 10 GS/s. Moreover, we analyze the energy consumption for synaptic operation, considering the full end-to-end system, which includes the transceivers, the optical neural network, and the electrical control part. This investigation shows that when the number of synapses/neuron is &amp;gt;18, the energy per operation is &amp;lt;20 pJ (6 times higher than when considering only the optical engine). The computation speed of this two-layer all-optical neural network system is 47 TMAC/s, 2.5 times faster than state-of-the-art graphics processing units, while the energy efficiency is 12 pJ/MAC, 2 times better. This result underlines the importance of scaling photonic integrated neural networks on chip.

Robust light beam diffractive shaping based on a kind of compact all-optical neural network.

A kind of compact all-optical learning-based neural network has been constructed and characterized for efficiently performing a robust layered diffractive shaping of laser beams. The data-driven control lightwave strategy demonstrates some particular advantages such as smart or intelligent light beam manipulation, optical data statistical inference and incident beam generalization. Based on the proposed method, several typical aberrated light fields can be effectively modulated into the desired fashion including the featured flat-top beams, an arrayed sub-beam arrangement and complex annular fringes compared with conventional GS-based DOEs. An actual THz laser is utilized to evaluate the effectiveness of the method developed.

The Winner-Take-All Mechanism for All-Optical Systems of Pattern Recognition and Max-Pooling Operation

The winner-take-all (WTA) mechanism based on the inhibitory dynamics of vertical-cavity surface-emitting laser with an embedded saturable absorber (VCSEL-SA) neurons is proposed for the first time. The WTA mechanism is shown numerically in a photonic spiking neural network (SNN). The effect of bias current on WTA time window is analyzed based on the proposed SNN. Moreover, a pattern recognition approach is presented numerically based on the WTA mechanism in all-optical neural network consisting of VCSEL-SA neurons. For the pattern recognition, the robustness of noisy inputs is examined. The effects of bias current, strength of inhibition and weight matrix on the speed of pattern recognition are analyzed carefully. Furthermore, the max-pooling operation is implemented numerically in the all-optical VCSEL-SA neural network model based on the WTA mechanism for the first time. The results hold great promise for the development of energy-efficient and high-speed photonic spiking neural network.

All-optical neural network with nonlinear activation functions

Artificial neural networks (ANNs) have now been widely used for industry applications and also played more important roles in fundamental researches. Although most ANN hardware systems are electronically based, optical implementation is particularly attractive because of its intrinsic parallelism and low energy consumption. Here, we propose and demonstrate fully-functioned all optical neural networks (AONNs), in which linear operations are programmed by spatial light modulators and Fourier lenses, and optical nonlinear activation functions are realized with electromagnetically induced transparency in laser-cooled atoms. Moreover, all the errors from different optical neurons here are independent, thus the AONN could scale up to a larger system size with final error still maintaining in a similar level of a single neuron. We confirm its capability and feasibility in machine learning by successfully classifying the order and disorder phases of a typical statistic Ising model. The demonstrated AONN scheme can be used to construct various ANNs of different architectures with the intrinsic parallel computation at the speed of light.

Class-specific differential detection in diffractive optical neural networks improves inference accuracy

Diffractive deep neural networks have been introduced earlier as an optical machine learning framework that uses task-specific diffractive surfaces designed by deep learning to all-optically perform inference, achieving promising performance for object classification and imaging. Here we demonstrate systematic improvements in diffractive optical neural networks based on a differential measurement technique that mitigates the non-negativity constraint of light intensity. In this scheme, each class is assigned to a separate pair of photodetectors, behind a diffractive network, and the class inference is made by maximizing the normalized signal difference between the detector pairs. Moreover, by utilizing the inherent parallelization capability of optical systems, we reduced the signal coupling between the positive and negative detectors of each class by dividing their optical path into two jointly-trained diffractive neural networks that work in parallel. We further made use of this parallelization approach, and divided individual classes among multiple jointly-trained differential diffractive neural networks. Using this class-specific differential detection in jointly-optimized diffractive networks, our simulations achieved testing accuracies of 98.52%, 91.48% and 50.82% for MNIST, Fashion-MNIST and grayscale CIFAR-10 datasets, respectively. Similar to ensemble methods practiced in machine learning, we also independently-optimized multiple differential diffractive networks that optically project their light onto a common detector plane, and achieved testing accuracies of 98.59%, 91.06% and 51.44% for MNIST, Fashion-MNIST and grayscale CIFAR-10, respectively. Through these systematic advances in designing diffractive neural networks, the reported classification accuracies set the state-of-the-art for an all-optical neural network design.

Solitary and coupled semiconductor ring lasers as optical spiking neurons

We theoretically investigate the possibility of generating pulses in an excitable (asymmetric) semiconductor ring laser (SRL) using optical trigger pulses. We show that the phase difference between the injected field and the electric field inside the SRL determines the direction of the perturbation in phase space. Due to the folded shape of the excitability threshold, this has an important influence on the ability to cross it. A mechanism for exciting multiple consecutive pulses using a single trigger pulse (i.e., multipulse excitability) is revealed. We furthermore investigate the possibility of using asymmetric SRLs in a coupled configuration, which is a first step toward an all-optical neural network using SRLs as building blocks.

All fiber-optic neural network using coupled SOA based ring lasers

An all-optical neural network is presented that is based on coupled lasers. Each laser in the network lases at a distinct wavelength, representing one neuron. The network status is determined by the wavelength of the network's light output. Inputs to the network are in the optical power domain. The nonlinear threshold function required for neural-network operation is achieved optically by interaction between the lasers. The behavior of the coupled lasers is explained by a simple laser model developed in the paper. In particular, the winner take all (WTA) neural-network behavior of a system of many lasers is described. An experimental system is implemented using single mode fiber optic components at wavelengths near 1550 nm. A number of functions are implemented to demonstrate the practicality of the new network. The neural network is particularly robust against input wavelength variations.

Optical-mode neural network by use of the nonlinear response of a laser diode to external optical feedback

We present an intelligent all-optical neural network using a single laser diode that is provided with controlled external feedback. The outputs of the laser neural network (LNN) are represented in the optical domain by the longitudinal cavity modes of the laser diode. The inputs to the LNN are applied by means of adjusting the external feedback of each longitudinal mode through an optical vector-matrix multiplier. Supervised training of some basic input-output mappings is demonstrated by means of a stochastic learning algorithm. The stability and reproducibility of the LNN setup is examined.

A New Optical Neuron Device for All-Optical Neural Networks

A new optical neuron device has been developed. The device can perform both summation and thresholding operations in optics, and consists of a PIN a-Si:H photoreceptor, aluminum neuron electrodes and a ferroelectric liquid crystal light modulator. The a-Si:H photoreceptor shows characteristics of an ideal quantum efficiency (η∼1) and a good linearity (γ∼1). The optical neuron device exhibits a response time of ∼30 µs for incident light power of 9 µW and a contrast ratio of 300:1. Using this neuron device, a lenslet array and a memory mask, an all-optical neural network has been constructed. The network demonstrates an associative memory function on purely optical parallel processing without any help from electric computation.

All-optical bipolar neural network with polarization-modulating neurons

A general all-optical implementation scheme for bipolar neural networks is presented. Bipolar operation is realized by exploiting two orthogonal light polarizations. A three-layer feed-forward bipolar network is demonstrated experimentally by using a liquid-crystal light valve for implementing an array of polarization modulating neurons.