A hybrid optical neural network with diverse parameterized layers for multifunctional intelligent processing

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.

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.

Artificial intelligence has prevailed in all trades and professions due to the assistance of big data resources, advanced algorithms, and high-performance electronic hardware. However, conventional computing hardware is inefficient at implementing complex tasks, in large part because the memory and processor in its computing architecture are separated, performing insufficiently in computing speed and energy consumption. In recent years, optical neural networks (ONNs) have made a range of research progress in optical computing due to advantages such as sub-nanosecond latency, low heat dissipation, and high parallelism. ONNs are in prospect to provide support regarding computing speed and energy consumption for the further development of artificial intelligence with a novel computing paradigm. Herein, we first introduce the design method and principle of ONNs based on various optical elements. Then, we successively review the non-integrated ONNs consisting of volume optical components and the integrated ONNs composed of on-chip components. Finally, we summarize and discuss the computational density, nonlinearity, scalability, and practical applications of ONNs, and comment on the challenges and perspectives of the ONNs in the future development trends.

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.

Optical neural networks (ONNs) have emerged as promising architectures for vision tasks due to their inherent parallelism and potential low energy consumption. Currently, achieving reconfigurable nonlinear optical activation with high responsiveness remains challenging in ONNs. In this study, we propose a reconfigurable configuration utilizing two-dimensional (2D) material-based inorganic liquid crystal (LC) as an optical-to-optical nonlinear activator. The ultrasensitive electro-optical effect of 2D vermiculite (VMT) enables the proposed configuration, where the nonlinear activation is sensitively modulated by a small operational electric field in a range of <0.4 V mm-1, orders of magnitude lower than other LCs. We validate the capability and feasibility of the 2D VMT inorganic LC-based nonlinear optical activator for ONNs through emulation on benchmark data sets for image recognition with accuracy of 99.69, 92.56, and 79.19% for MNIST, Fashion-MNIST, and CIFAR-10, respectively. This work shows the potential of 2D material inorganic LCs as activators in ONNs, offering promising avenues for future advanced computational applications.

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.

We propose Si microring resonator (MRR) crossbar arrays as a programmable nanophotonoic processor (PNP) for a deep learning accelerator. The proposed MRR crossbar array can perform multiply-accumulate (MAC) operation in an optical domain. We numerically reveal that an optical neural network (ONN) based on the proposed MRR crossbar arrays can be used for the pattern recognition task with a similar performance to that of an ONN based on cascaded Mach–Zehnder interferometers. We predict that the power consumption can be reduced by approximately tenfold. The small area of the MRR also contributes to the reduction in its chip size by a factor of 36. The fabricated test devices consisting of Si MRRs with phase shifters exhibited no significant crosstalk between neighboring MRRs and showed the feasibility of MAC operation. Photonic integrated circuit using the proposed MRR crossbar arrays is promising for large-scale and low-power PNP for deep learning.

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.

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 neuromorphic computing has demonstrated promising performance with ultra-high computation speed, high bandwidth, and low energy consumption. The traditional optical neural network (ONN) architectures realize neuromorphic computing via electrical weight encoding. However, previous ONN design methodologies can only handle static linear projection with stationary synaptic weights, thus fail to support efficient and flexible computing when both operands are dynamically-encoded light signals. In this work, we propose a novel ONN engine O2NN based on wavelength-division multiplexing and differential detection to enable high-performance, robust, and versatile photonic neural computing with both light operands. Balanced optical weights and augmented quantization are introduced to enhance the representability and efficiency of our architecture. Static and dynamic variations are discussed in detail with a knowledge-distillation-based solution given for robustness improvement. Discussions on hardware cost and efficiency are provided for a comprehensive comparison with prior work. Simulation and experimental results show that the proposed ONN architecture provides flexible, efficient, and robust support for high-performance photonic neural computing with fully-optical operands under low-bit quantization and practical variations.

The massive interconnection and parallel operation in an optical neural network (ONN) require a high-resolution, large-dynamic-range spatial light modulator (SLM) for the construction of the interconnectionweight matrix (IWM). However, the resolution of currently available SLM's is limited, and this is a major obstacle in the development of a large-scale optical neural computers. We use a space-time-sharing technique to improve the resolution of an optical neural operation. Because the ONN we recently developed1 uses incoherent light, the space–bandwidth product of the network can be expanded by space-time multiplexing. In other words, a large-scale neural operation can be accomplished with a smaller network, by trading off the processing speed. To accomplish this task, we have shown that a large-scale IWM can be partitioned into arrays of sub-IWM's, of which the space–bandwidth product of the sub-IWM's is equal to the number of neurons in the neural network. Then by sequentially displaying these arrays of sub-IWM's, a larger (nfold) space–bandwidth image pattern can be obtained by using a smaller ONN. Computer-simulated results and experimental demonstrations are also provided in this paper.

The rapid growth in computing demands, particularly driven by artificial intelligence applications, has begun to exceed the capabilities of traditional electronic hardware. Optical computing offers a promising alternative due to its parallelism, high computational speed, and low power consumption. However, existing photonic integrated circuits are constrained by large footprints, costly electro-optical interfaces, and complex control mechanisms, limiting the practical scalability of optical neural networks (ONNs). To address these limitations, we introduce a block-circulant photonic tensor core for a structure-compressed optical neural network (StrC-ONN) architecture. The structured compression technique substantially reduces both model complexity and hardware resources without sacrificing the versatility of neural networks, and achieves accuracy comparable to uncompressed models. Additionally, we propose a hardware-aware training framework to compensate for on-chip nonidealities to improve model robustness and accuracy. Experimental validation through image processing and classification tasks demonstrates that our StrC-ONN achieves a reduction in trainable parameters of up to 74.91%, while still maintaining competitive accuracy levels. Performance analyses further indicate that this hardware–software co-design approach is expected to yield a 3.56× improvement in power efficiency. By reducing both hardware requirements and control complexity across multiple dimensions, this work explores a pathway toward practical and scalable ONNs, highlighting a promising route to address future computational efficiency challenges.

The rise of Artificial Intelligence (AI) in our society is becoming ubiquitous and undoubtedly holds much promise. However, AI has also been implicated in high profile breaches of trust or ethical standards, and concerns have been raised over the use of AI in initiatives and technologies that could be inimical to society. Public trust and perceptions of AI trustworthiness underpin AI systems’ social licence to operate, and a myriad of company, industry, governmental and intergovernmental reports have set out principles for ethical and trustworthy AI. To guide the responsible stewardship of AI into our society, a firm foundation of research on trust in AI to enable evidence-based policy and practice is required. However, in order to inform and guide future research, it is imperative to first take stock and understand what is already know about human trust in AI. As such, we undertake a review of 100 papers examining the relationship between trust and AI. We found a fragmented, disjointed and siloed literature with an empirical emphasis on experimentation and surveys relating to specific AI technologies. While findings suggest some convergence on the importance of explainability as a determinant of trust in AI technologies, there are still gaps between conceptual arguments and what has been examined empirically. We urge future research to take a more holistic approach and investigate how trust in different referents impacts on attitudinal and behavioural intentions. Doing so will facilitate a more nuanced understanding of what it means to develop trustworthy AI.

The research relevance is determined by the importance of a thorough study of methods, schemes and models used by artificial intelligence to mechanise creativity in modern conditions of active technological development. The study aims to analyse the main processes taking place in modern art in connection with active technologization of work processes, to identify the leading concepts regarding the possibility of creating machine art in the future, etc. The employed methods are theoretical, such as analysis, systematisation, generalisation, etc., for studying key problems and further development of creativity based on artificial intelligence. The study examines in detail the main developments of Artificial General Intelligence and Artificial Narrow Intelligence, in particular the achievements of Generative adversarial networks and Creative adversarial networks. Artificial intelligence-generated art demonstrates the remarkable capabilities of technologies. The evolving artificial intelligence in the arts introduces “digital art”. Generative Adversarial Networks are used as a foundational tool for artists who use digital methods and texture generation to create unique compositions. Furthermore, sculptors collaborate with artificial intelligence tools to convert drawings into 3D models or transform historical art databases into sculptures. Creative thinking, a hallmark of human intelligence, is determined as artificial intelligence’s ability to generate new and original ideas. The development of emotional intelligence in artificial intelligence enables empathetic responses and the identification of human emotions through voice and facial expressions. The issues of authorised internationality, awareness of the creative process, psychological foundations of artificial empathy and emotional intelligence define the prospects for the development of neuroscience. Challenges persist in defining creativity, authorship, and legal aspects of artificial intelligence-generated art. The study materials may be useful for artists, art educators, technologists, and researchers interested in the intersection of technology and art, legal professionals (especially intellectual property law), and individuals involved in artificial intelligence development may find these findings valuable

In emerging artificial intelligence applications, massive matrix operations require high computing speed and energy efficiency. Optical computing can realize high-speed parallel information processing with ultra-low energy consumption on photonic integrated platforms or in free space, which can well meet these domain-specific demands. In this review, we firstly introduce the principles of photonic matrix computing implemented by three mainstream schemes, and then review the research progress of optical neural networks (ONNs) based on photonic matrix computing. In addition, we discuss the advantages of optical computing architectures over electronic processors as well as current challenges of optical computing and highlight some promising prospects for the future development.