English
Related papers

Related papers: Optical activation function using a metamaterial w…

200 papers

Non-degenerate two-photon absorption (TPA) is investigated in a nanophotonic silicon waveguide in a configuration such that the dispersion of the nonlinear absorption and refraction cannot be neglected. It is shown that a signal wave can…

Addressing the imperative need for efficient artificial intelligence in IoT and edge computing, this study presents RepAct, a re-parameterizable adaptive activation function tailored for optimizing lightweight neural networks within the…

Machine Learning · Computer Science 2024-07-02 Xian Wu , Qingchuan Tao , Shuang Wang

We present a deep learning approach using an optical neural network to predict the fundamental modal indices $n_{\rm{eff}}$ in a silicon (Si) channel waveguide. We use three inputs, e.g., two geometric parameters and one material property,…

Optics · Physics 2020-08-04 Nusrat Jahan Anika , Md Borhan Mia

An activation function has a significant impact on the efficiency and robustness of the neural networks. As an alternative, we evolved a cutting-edge non-monotonic activation function, Negative Stimulated Hybrid Activation Function (Nish).…

Machine Learning · Computer Science 2022-12-20 Yildiray Anagun , Sahin Isik

Nanoscale slot waveguides of hyperbolic metamaterials are proposed and demonstrated for achieving large optical field enhancement. The dependence of the enhanced electric field within the air slot on waveguide mode coupling and permittivity…

Optics · Physics 2015-06-04 Yingran He , Sailing He , Xiaodong Yang

Topological insulators (TI) are highly attractive platforms for next-generation optoelectronic and photonic devices. Spin-momentum locking of topological surface states enhance their nonlinear optical responses and sensitivities, especially…

Other Condensed Matter · Physics 2026-02-03 Hamideh Sharifpour , George J. de Coster , Avik W. Ghosh

We study an integrated silicon photonic chip, composed of several sub-wavelength ridge waveguides, and immersed in a micro-cell with rubidium vapor. Employing two-photon excitation, including a telecom wavelength, we observe that the…

Motivated by the growing theoretical understanding of neural networks that employ the Rectified Linear Unit (ReLU) as their activation function, we revisit the use of ReLU activation functions for learning implicit neural representations…

Image and Video Processing · Electrical Eng. & Systems 2024-08-05 Joseph Shenouda , Yamin Zhou , Robert D. Nowak

The extraordinary properties of nonlinear optical propagation processes in double-domain positive/negative index metamaterials are reviewed. These processes include second harmonic generation, three- and four-wave frequency mixing, and…

Optics · Physics 2012-04-02 Alexander K. Popov , Vladimir M. Shalaev

Abbe diffraction limit fundamentally bounds the resolution of conventional optical imaging and spectroscopic systems. Along the years, several schemes have been introduced to overcome this limit, each offering opportunities and trade-offs.…

Classical Physics · Physics 2023-04-03 Seunghwi Kim , Yu-Gui Peng , Simon Yves , Andrea Alù

We design and model a single-layer, passive, all-optical silicon photonics neural network to mitigate optical link nonlinearities. The network nodes are formed by silicon microring resonators whose transfer function has been experimentally…

Signal Processing · Electrical Eng. & Systems 2021-03-01 Mattia Mancinelli , Paolo Bettotti , Lorenzo Pavesi

We demonstrate that the broadband nonlinear optical response of graphene can be resonantly enhanced by more than an order of magnitude through hybridization with a plasmonic metamaterial,while retaining an ultrafast nonlinear response time…

The choice of activation function in deep networks has a significant effect on the training dynamics and task performance. At present, the most effective and widely-used activation function is ReLU. However, because of the non-zero mean,…

Computer Vision and Pattern Recognition · Computer Science 2020-03-03 Yuan Zhou , Dandan Li , Shuwei Huo , Sun-Yuan Kung

It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly…

Machine Learning · Computer Science 2020-04-13 Abhishek Panigrahi , Abhishek Shetty , Navin Goyal

In this paper, we propose novel quaternion activation functions where we modify either the quaternion magnitude or the phase, as an alternative to the commonly used split activation functions. We define criteria that are relevant for…

Machine Learning · Computer Science 2024-06-25 Johannes Pöppelbaum , Andreas Schwung

Activation functions play a decisive role in determining the capacity of Deep Neural Networks as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Jamshaid Ul Rahman , Faiza Makhdoom , Dianchen Lu

In this paper, a photonic crystal containing graphene and metamaterial layers is investigated. The absorption spectrum of the structure in the terahertz range is obtained using the transfer matrix method. The results show that by adding a…

Applied Physics · Physics 2019-10-15 M. Montaseri , M. Hosseini , M. J. Karimi

Advances in silicon (Si) photonics at submicrometer wavelengths are unlocking new opportunities to realize miniaturized, scalable optical systems for biophotonics, quantum information, imaging, spectroscopy, and displays. Addressing this…

The ability to exploit the on-chip nonlinear generation of new frequencies has opened the door to a plethora of applications in fundamental and applied physics. Excitation of dispersive waves is a particularly interesting process that…

Activation functions have come up as one of the essential components of neural networks. The choice of adequate activation function can impact the accuracy of these methods. In this study, we experiment for finding an optimal activation…

Machine Learning · Computer Science 2022-02-25 Vipul Bansal
‹ Prev 1 3 4 5 6 7 10 Next ›