Optical neural networks with terminal attractors for pattern recognition

Event Abstract Back to Event Logarithmic Hybrid Optical Neural Network-type systems: towards digital-optical cognitive models of robust object recognition Ioannis Kypraios1* 1 Oxford University, Centre for Innovation & Enterprise, APEM Computing Lab, United Kingdom Abstract - By combining the complex logarithmic r-theta mapping of a space-variant imaging sensor [1, 2] with the hybrid digital-optical neural network filter together with a window unit multiple objects of the same class or of different classes can robustly be recognized. The resulted logarithmic r-theta mapping for hybrid digital-optical neural network system or briefly referred to as logarithmic hybrid optical neural network system is shown to exhibit with a single pass over the input data simultaneously in-plane rotation, out-of-plane rotation, scale, log r-θ map translation and shift invariance, and good clutter tolerance by recognizing correctly the different objects within the cluttered scenes. Here, we study the biologically-inspired knowledge learning and knowledge representation [3] achieved by the logarithmic hybrid optical neural network-type of object recognition systems (see Fig. 1 and Fig. 2). We investigate the effects that altering the knowledge representation can have on the problem’s learned knowledge and the problem solving process, in overall. Further, we study the logarithmic unconstrained-, logarithmic constrained-, and logarithmic modified-hybrid optical neural network systems architectures’ designs [4, 5]. We show how the logarithmic unconstrained-hybrid optical neural network object recognition system applies an unconstrained representation of the problem’s knowledge to maximize the search of solutions, how the logarithmic constrained-hybrid optical neural network object recognition system uses a constrained representation of the problem’s knowledge to guide the search towards certain solutions over others in the multidimensional search space, and how the logarithmic modified-hybrid optical neural network object recognition system uses memory-like masks to recall certain solutions over others in the multidimensional search space. Fig. 1. (a) Simplified human retina and visual cortex model used for description purposes only; (b) A digital-optical computational model for the cognitive interaction between the retina and the human visual cortex with the general logarithmic hybrid optical neural network architercture. Fig. 2. Biologically-inspired knowledge learning and knowledge representation with the logarithmic hybrid optical neural network-type of object recognition systems. Figure 1 Figure 2 References [1] C. F. R. Weiman, “Video compression via log-polar mapping”, Real-Time Image Processing II, SPIE Symposium on OE/Aerospace Sensing, Vol. 1295, 266-277 (1990) [2] C. G. Ho et al., “Sensor geometry and sampling methods for space-variant image processing”, Pattern Analysis and Applications, Vol. 5, 369-384 (2002) [3] I. Lee, and B. Portier, "An empirical study of knowledge representation and learning within conceptual spaces for intelligent agents", 6th IEEE/ACIS International Conference Computer and Information Science, 463-468, Melbourne, Australia (2007) [4] I. Kypraios et al., “Fully invariant complex Logarithmic r- map for the Hybrid Optical Neural Network filter for object recognition within cluttered scenes”, 50th Anniversary International Symposium ELMAR 2008, IEEE Region 8/IEEE Croatia Section/EURASIP, Zadar-Croatia, Vol. 1, 141-146 (2008) [5] I. Kypraios et al., “Logarithmic r-θ mapping for hybrid optical neural network filter for object recogntion within cluttered scenes”, Recent Advances in Multimedia Signal Processing and Communications, SCI231, Springer-Verlag Berlin Heidelberg, 91-120 (2009) Keywords: digital-optical, cognitive, object recognition, Robust and Adaptive Systems, Knowledge representation, learning and memory Conference: Neuroinformatics 2013, Stockholm, Sweden, 27 Aug - 29 Aug, 2013. Presentation Type: Poster Topic: Neuromorphic engineering Citation: Kypraios I (2013). Logarithmic Hybrid Optical Neural Network-type systems: towards digital-optical cognitive models of robust object recognition. Front. Neuroinform. Conference Abstract: Neuroinformatics 2013. doi: 10.3389/conf.fninf.2013.09.00066 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 09 Apr 2013; Published Online: 11 Jul 2013. * Correspondence: Dr. Ioannis Kypraios, Oxford University, Centre for Innovation & Enterprise, APEM Computing Lab, Begbroke, Oxfordshire, OX5 1PF, United Kingdom, ioanniskyp@yahoo.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Ioannis Kypraios Google Ioannis Kypraios Google Scholar Ioannis Kypraios PubMed Ioannis Kypraios Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

A novel configuration of an optical lateral inhibitory neural network using a two-dimensional internal-light-coupled optical device (ILCOD) array is proposed. It is experimentally certified with a test ILCOD structured with seven units in a two-dimensional hexagonal arrangement that the optical coupling between the units causes turn-off of the light emission of the unit in a specific position, which results in lateral inhibitory action of a neural network.

Optical associative memory with terminal attractor (TA) is proposed for pattern recognition. With numerical simulations, the optimal control parameter in the TA model associative memory is determined. The optimal control parameter is also used in an optical experiment. The capacity of TA model associative memory is also investigated based on the consistency between the stored pattern and the obtained equilibrium state in statistical thermodynamics. The results of numerical simulations indicate that the memory rate of the TA associative memory is greater than 0.35. We also compare TA model with the conventional Hopfield model, and show that the TA model can eliminate spurious states in the Hopfield model and increase recalling ability and memory capacity.

The growing computational demands of artificial intelligence motivate the development of optical neural networks (ONNs), while their practical deployment remains constrained by optimization complexity and limited adaptability. We propose a mutual learning knowledge distillation framework for optical diffractive neural networks (ODNNs), synergizing photonic computing with adaptive training strategies. Our architecture enables bidirectional knowledge transfer between parameter-efficient optical student networks and electrical ResNet teachers, leveraging both labeled data and probabilistic guidance. The validation on Fashion-MNIST and Kuzushiji-MNIST demonstrates classification accuracy improvements of 5.9% and 13.88%, respectively, over conventional ODNNs training. In addition, we further developed the photonic to photonic mutual learning computational paradigm, in which an optical network with 0.98 × 106 parameters can bootstrap compact photonic classifiers with 0.19 × 106 parameters, achieving an accuracy of 79.5% on MNIST and yielding an absolute improvement of 9% relative to the noncooperative baseline. Even though the all-optical mutual learning paradigm still has a gap of about 19% with the state-of-the-art ODNNs, the number of parameters of the guided student networks is smaller than the state-of-the-art networks by several or even dozens of times. These results establish a paradigm for overcoming fundamental limitations in ONN optimization, paving the way for a new era in which ONNs can solve large-scale practical problems through photonic–electronic and photonic–photonic co-design.

A transmissive liquid crystal valve for carrying out optical thresholding operations is proposed. It operates in parallel, that is, all the pixels of input are processed together simultaneously. The device is based on an amorphous silicon photoconductor and the features of liquid crystals. It does not require control architecture using very large scale integration (VLSI), so we can achieve a larger aperture ratio, higher resolution (more than 45 lines/mm), and a higher space-bandwidth prod- uct (more than 4310 5 pixels). Its response time is about 10 ms. Its processing capacity can reach approximately 2310 7 thresholding operations/s. The light valve does not break the beam propagation path, and can plug and play easily in optical processing and neural network systems. Its design, fabrication, and thresholding features are presented. © 1996 Society of Photo-Optical Instrumentation Engineers.

Machine learning with artificial neural networks has recently transformed many scientific fields by introducing new data analysis and information processing techniques. Despite these advancements, efficient implementation of machine learning on conventional computers remains challenging due to speed and power constraints. Optical computing schemes have quickly emerged as the leading candidate for replacing their electronic counterparts as the backbone for artificial neural networks. Some early integrated photonic neural network (IPNN) techniques have already been fast-tracked to industrial technologies. This review article focuses on the next generation of optical neural networks (ONNs), which can perform machine learning algorithms directly in free space. We have aptly named this class of neural network model the free space optical neural network (FSONN). We systematically compare FSONNs, IPNNs, and the traditional machine learning models with regard to their fundamental principles, forward propagation model, and training process. We survey several broad classes of FSONNs and categorize them based on the technology used in their hidden layers. These technologies include 3D printed layers, dielectric and plasmonic metasurface layers, and spatial light modulators. Finally, we summarize the current state of FSONN research and provide a roadmap for its future development.

While numerous artificial neural network (ANN) models have been electronically implemented and simulated by conventional computers, optical technology provides a far superior mechanism for the implementation of large-scale ANNs. The properties of light make it an ideal carrier of data signals. With optics, very large and high speed neural network architectures are possible. Because light is a predictable phenomenon, it can be described mathematically and its behavior can be simulated by conventional computers. A hologram is in essence a capture of the light field at a particular moment in time and space. Later, the hologram can be used to reconstruct the three dimensional light field carrying optical data. This makes a hologram an ideal medium for capturing, storing, and transmitting data in optical computers, such as optical neural networks (ONNs). Holograms can be created using conventional methods, but they can also be computer generated. In this paper, we will present an overview of optical neural networks, with emphasis on the holographic neural networks. We will take a look at the mathematical basis of holography in terms of the Fresnel Zone Plate and how it can be utilized in making computer generated holograms (CGHs). Finally, we will present various methods of CGH implementation in a two layer holographic ONN.

Optoelectronic realization of adaptive filters and equalizers using fiber optic tapped delay lines and spatial light modulators has been discussed recently. We describe the design of a single layer fiber optic Adaline neural network which can be used as a bit pattern classifier. In our realization we employ as few electronic devices as possible and use optical computation to utilize the advantages of optics in processing speed, parallelism, and interconnection. The new optical neural network described in this paper is designed for optical processing of guided lightwave signals, not electronic signals. We analyzed the convergence or learning characteristics of the optically implemented Adaline in the presence of errors in the hardware, and we studied methods for improving the convergence rate of the Adaline.© (1993) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

In recent years, with the expansion of information, artificial intelligence technology has been developed and used in various fields. Among them, optical neural network provides a new type of special neural network accelerator chip solution, which has the advantages of high speed, high bandwidth, and low power consumption. In this paper, we construct an optical neural network based on Mach–Zehnder interferometer. The experimental results on the image classification of MNIST handwritten digitals show that the optical neural network has high accuracy, fast convergence and good scalability.

Having considered all the constraints of the job-shop scheduling problem (JSP), we present a new computational energy function of Hopfield neural networks for JSP. By introducing transient chaos and time-variant gain, an improved method to solve JSP by a neural network model with transient chaos is proposed, which can avoid Hopfield neural networks being sucked into local minima. The simulation results show that the modified method not only has the ability of searching for the global minimum, but can also converge to minimum quickly. More importantly, it can keep the steady output of neural networks as a feasible solution for JSP.

We have developed a novel framework for combining physics-based forward models and neural networks to advance seismic processing and inversion algorithms. Migration is an effective tool in seismic data processing and imaging. Over the years, the scope of these algorithms has broadened; today, migration is a central step in the seismic data processing workflow. However, no single migration technique is suitable for all kinds of data and all styles of acquisition. There is always a compromise on the accuracy, cost, and flexibility of these algorithms. On the other hand, machine-learning algorithms and artificial intelligence methods have been found immensely successful in applications in which big data are available. The applicability of these algorithms is being extensively investigated in scientific disciplines such as exploration geophysics with the goal of reducing exploration and development costs. In this context, we have used a special kind of unsupervised recurrent neural network and its variants, Hopfield neural networks and the Boltzmann machine, to solve the problems of Kirchhoff and reverse time migrations. We use the network to migrate seismic data in a least-squares sense using simulated annealing to globally optimize the cost function of the neural network. The weights and biases of the neural network are derived from the physics-based forward models that are used to generate seismic data. The optimal configuration of the neural network after training corresponds to the minimum energy of the network and thus gives the reflectivity solution of the migration problem. Using synthetic examples, we determine that (1) Hopfield neural networks are fast and efficient and (2) they provide reflectivity images with mitigated migration artifacts and improved spatial resolution. Specifically, the presented approach minimizes the artifacts that arise from limited aperture, low subsurface illumination, coarse sampling, and gaps in the data.

Automation of optical system design is one of the key directions in modern optical engineering. The combination of physically grounded simulators, numerical optimization techniques, and machine-learning algorithms enables the development of compact, energy-efficient, and manufacturable optical systems. However, the high dimensionality of parameter spaces, significant computational costs, and the lack of unified verification criteria necessitate a systematic analysis of the applicability of different methods. The article presents a systematization of current approaches to optical system design automation, an analysis of their key characteristics, and an assessment of prospects for further development. Five main classes of methods are examined: differentiable physical models, deep-learning algorithms, evolutionary and metaheuristic optimizers, hybrid schemes combining machine learning methods and physics-based modeling, and fully forward (optical) training approaches. Consideration is given to the formation of a unified comparison framework that enables objective evaluation of speed, accuracy, reliability, robustness, generalization capability, computational complexity, and energy efficiency across different algorithms. A classification of automated optical design methods is proposed. The analysis includes physical models, neural-network architectures, and optimization algorithms. A comparative evaluation based on a unified set of metrics is provided, including qualitative and quantitative assessments derived from peer-reviewed publications from 2019 to 2025. The study demonstrates that differentiable physical methods provide the highest level of physical fidelity and accuracy. Deep-learning methods ensure maximal speed of solution generation. Evolutionary algorithms exhibit robustness against local minima. Hybrid approaches offer an effective balance between speed and physical correctness. Fully forward training methods (FFM approaches) and optical neural networks deliver high energy efficiency and show potential for hardware acceleration of the design process. The results can serve as a basis for selecting design strategies for optical systems across tasks of varying complexity — from preliminary configuration search to high-precision optimization. Progress in automated optical system design is linked to further standardization of datasets, integration of hybrid approaches, and the advancement of optical neural networks

In 1984 Hopfield showed that the time evolution of a symmetric Hopfield neural networks are a motion in state space that seeks out minima in the energy function (i.e., equilibrium point set of Hopfield neural networks). Because high-order Hopfield neural networks have more extensive applications than Hopfield neural networks, and have been discussed on the convergence of the networks. In practice, a neural network is often subject to environmental noise. It is therefore useful and interesting to find out whether the high-order neural network system still approacher some limit set under stochastic perturbation. In this paper, we will give a number of useful bounds for the noise intensity under which the stochastic high-order neural network will approach its limit set. Our result cancels the requirement of symmetry of the connection weight matrix and includes the classic result on Hopfield neural networks, which is a special case of stochastic high-order Hopfield neural networks. In the end, A example is given to verify the effective of our results.

Inspired by neural networks based on traditional electronic circuits, optical neural networks (ONNs) show great potential in terms of computing speed and power consumption. Though some progress has been made in devices and schemes, ONNs are still a long way from replacing electronic neural networks in terms of generalizability. Here, we present a complex optical neural network (cONN) for holographic image recognition, within which a high-speed parallel operating unit for complex matrices is proposed, targeting the real-imaginary-splitting and column splitting. Based on the proposed cONN, we have numerically demonstrated the training-recognition process on our cONN for holographic images converted from handwritten digit datasets, achieving an accuracy of 90% based on the back-propagation algorithm. Our training-verification integrated architecture will enrich the further development and applications of on-chip photonic matrix computing.

Supplemental document