Related papers: Optical activation function using a metamaterial w…
Photonic neural networks benefit from both the high channel capacity- and the wave nature of light acting as an effective weighting mechanism through linear optics. The neuron's activation function, however, requires nonlinearity which can…
The ability to engineer metamaterials with tunable nonlinear optical properties is crucial for nonlinear optics. Traditionally, metals have been employed to enhance nonlinear optical interactions through field localization. Here, inspired…
Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear…
Image processing is both one of the most exciting domains for applying artificial intelligence and the most computationally expensive. Nanostructured metasurfaces have opened the door to the ultimate energy saving by directly processing…
To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in the data. In this…
Activation functions are essential to introduce nonlinearity into neural networks, with the Rectified Linear Unit (ReLU) often favored for its simplicity and effectiveness. Motivated by the structural similarity between a shallow…
At the first glance, the expression "transparent superconductor" may seem an oxymoron. Still, the first principle calculations and experiments show that the materials that behave as superconductors at low frequencies and do not absorb in…
Due to the limitations of Moore's Law and the increasing demand of computing, optical neural network (ONNs) are gradually coming to the stage as an alternative to electrical neural networks. The control of nonlinear activation functions in…
The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most…
Implicit Neural Representation (INR), leveraging a neural network to transform coordinate input into corresponding attributes, has recently driven significant advances in several vision-related domains. However, the performance of INR is…
Nonlinear absorption can limit the efficiency of nonlinear optical devices. However, it can also be exploited for optical limiting or switching applications. Thus, characterization of nonlinear absorption in photonic devices is imperative.…
We present a full-spectrum machine learning framework for refractive index sensing using simulated absorption spectra from meta-grating structures composed of titanium or silicon nanorods under TE and TM polarizations. Linear regression was…
Deep learning researchers have a keen interest in proposing two new novel activation functions which can boost network performance. A good choice of activation function can have significant consequences in improving network performance. A…
Many industrial and real life problems exhibit highly nonlinear periodic behaviors and the conventional methods may fall short of finding their analytical or closed form solutions. Such problems demand some cutting edge computational tools…
We study the approximation properties of shallow neural networks with an activation function which is a power of the rectified linear unit. Specifically, we consider the dependence of the approximation rate on the dimension and the…
The non-convex nature of trained neural networks has created significant obstacles in their incorporation into optimization models. In this context, Anderson et al. (2020) provided a framework to obtain the convex hull of the graph of a…
Nonlinear optical waveguides, particularly those harnessing the optical Kerr effect, are promising for advancing next-generation photonic technologies. Despite the Kerr effect`s ultrafast response, its inherently weak nonlinearity has…
Optical materials with vanishing dielectric permittivity, known as epsilon-near-zero (ENZ) materials, have been shown to possess enhanced nonlinear optical responses in their ENZ region. These strong nonlinear optical properties have been…
We propose \textbf{ULU}, a novel non-monotonic, piecewise activation function defined as $\{f(x;\alpha_1),x<0; f(x;\alpha_2),x>=0 \}$, where $f(x;\alpha)=0.5x(tanh(\alpha x)+1),\alpha >0$. ULU treats positive and negative inputs…
Activation functions have a notorious impact on neural networks on both training and testing the models against the desired problem. Currently, the most used activation function is the Rectified Linear Unit (ReLU). This paper introduces a…