&lt;title&gt;Two-Dimensional Matrix Multiplication using Coherent Optical Techniques&lt;/title&gt;

Tamura, Poohsan N.; Wyant, James C.

doi:10.1117/12.7972350

Cited by 14 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here we demonstrate a reconfigurable coherent optical multiplier with matrix size up to 56 × 56, an order of magnitude larger than achieved previously [3]. Our free-space system is capable of performing VMM, as well as parallel vector-vector multiplication (p-VVM), and our results are obtained using spatial light modulators (SLMs) with only 340 × 340 pixels.…”

Section: Introductionmentioning

confidence: 94%

“…Multiplication of matrices can be viewed as a set of vectormatrix multiplications (VMMs) implemented in concert. Various optical VMM (OVMM) systems have been proposed and demonstrated in both free space [2][3][4][5][6] and integrated photonic circuits [7][8][9]. Most free-space implementations are based on the Stanford multiplier design [2], where input vector values are encoded in the intensity of a horizontal array of incoherent light sources.…”

Section: Introductionmentioning

confidence: 99%

“…To handle negative or complex values, the multiplication must be decomposed and requires multiple optical setups, which increases the computational cost. In 1979, Tamura et al developed a coherent OVMM system to process real-valued operations [3]. However, technology of the time prevented reconfigurability and restricted the practical demonstration to binary matrices on photographic transparencies.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fully reconfigurable coherent optical vector-matrix multiplication

Spall,

Guo,

Barrett

et al. 2020

Preprint

View full text Add to dashboard Cite

Optics is a promising platform in which to help realise the next generation of fast, parallel and energyefficient computation. We demonstrate a reconfigurable free-space optical multiplier that is capable of over 3000 computations in parallel, using spatial light modulators with a pixel resolution of only 340 × 340. This enables vector-matrix multiplication and parallel vectorvector multiplication with vector size of up to 56. Our design is the first to simultaneously support optical implementation of reconfigurable, large-size and realvalued linear algebraic operations. Such an optical multiplier can serve as a building block of special-purpose optical processors such as optical neural networks and optical Ising machines.

show abstract

Section: Introductionmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully reconfigurable coherent optical vector-matrix multiplication

Spall,

Guo,

Barrett

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Silicon photonics [5] provide superior performance in energy consumption [6,7] and computational rate [8] over electronics, which has become an attractive platform. Photonic integrated circuits can easily realize matrix multiplication with the coherence and superposition of linear optics [9]. The advantages of photonics have promoted extensive demonstrations of various high-performance optical functionalities, especially in photon computing [10][11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Implementation of Pruned Backpropagation Neural Network Based on Photonic Integrated Circuits

2021

View full text Add to dashboard Cite

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.

show abstract

MXene‐Based Broadband Ultrafast Nonlinear Activator for Optical Computing

Yang

Tan

Zhang

et al. 2022

Advanced Optical Materials

View full text Add to dashboard Cite

Optical neural networks (ONNs) are particularly advantageous owing to their inherent parallelism and low energy consumption. However, one of the obstacles to the implementation of ONNs is the lack of optical nonlinearity. In this study, optical nonlinear activators for ONNs are prepared by combining Ti3C2Tx MXene with microfibers and their principles are verified. Activation functions obtained from experimental measurements are used to simulate multiclassification and super‐resolution reconstruction tasks with performance comparable to that of activation functions commonly used in computers. Four necessary criteria are proposed and validated for evaluating the performance of the nonlinear activator: recovery time, deviation from linearity, the activation function close to identity mapping, and reconfigurability of the configuration. Theoretically, the nonlinear activator can compute 100 times faster than commonly used electronic computers and can be used as a nonlinear activation unit for ONNs to help the integration of ONNs with artificial intelligence.

show abstract

<title>Two-Dimensional Matrix Multiplication using Coherent Optical Techniques</title>

Cited by 14 publications

References 6 publications

Fully reconfigurable coherent optical vector-matrix multiplication

Fully reconfigurable coherent optical vector-matrix multiplication

Implementation of Pruned Backpropagation Neural Network Based on Photonic Integrated Circuits

MXene‐Based Broadband Ultrafast Nonlinear Activator for Optical Computing

Contact Info

Product

Resources

About