Related papers: All-optical nonlinear activation function based on…
Integrated optical devices that can realize a threshold filtration of signals are in demand in photonics. In particular, they play a key role in neuromorphic chips, acting as optical neurons. A list of requirements exist for thresholders to…
In recent years, remarkable advances in photonic computing have highlighted the need for photonic memory, particularly high-speed and coherent random-access memory. Addressing the ongoing challenge of implementing photonic memories is…
Artificial neural networks usually consist of successive linear multiply-accumulate operations and nonlinear activation functions. However, most optical neural networks only achieve the linear operation in the optical domain, while the…
While nanoscale modal confinement radically enhances a variety of nonlinear light-matter interactions within silicon waveguides, traveling-wave stimulated Brillouin scattering nonlinearities have never been observed in silicon…
The expressive power of artificial neural networks crucially depends on the nonlinearity of their activation functions. Though a wide variety of nonlinear activation functions have been proposed for use in artificial neural networks, a…
Optical neural networks usually execute the linear multiply-accumulate operation in the optical domain, whereas the nonlinear activation function is mostly implemented in the digital or electrical domain. Here we demonstrate a broadband…
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…
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…
In the well-known stimulated Brillouin scattering (SBS) process, spontaneous acoustic phonons in materials are stimulated by laser light and scatter the latter into a Stokes sideband. SBS becomes more pronounced in optical fibers and has…
We extended the work of proposed activation function, Noisy Softplus, to fit into training of layered up spiking neural networks (SNNs). Thus, any ANN employing Noisy Softplus neurons, even of deep architecture, can be trained simply by the…
Stimulated Brillouin scattering (SBS) is a very fundamental interaction between light and travelling acoustic waves, which is mainly attributed to the electrostriction and photoelastic effects with the interaction strength being orders of…
In this paper, we explore the spatio-temporal dynamics of spontaneous and stimulated forward Brillouin scattering. This general treatment incorporates the optomechanical coupling produced by boundary-induced radiation pressures (boundary…
Nonlinear activation functions are widely recognized for enhancing the expressivity of neural networks, which is the primary reason for their widespread implementation. In this work, we focus on ReLU activation and reveal a novel and…
Achieving nonreciprocal light propagation in photonic circuits is essential to control signal crosstalk and optical back-scatter. However, realizing high-fidelity nonreciprocity in low-loss integrated photonic systems remains challenging.…
Photonic computing chips have made significant progress in accelerating linear computations, but nonlinear computations are usually implemented in the digital domain, which introduces additional system latency and power consumption, and…
Brillouin laser oscillators offer powerful and flexible dynamics as the basis for mode-locked lasers, microwave oscillators, and optical gyroscopes in a variety of optical systems. However, Brillouin interactions are exceedingly weak in…
The high demand for machine intelligence of doubling every three months is driving novel hardware solutions beyond charging of electrical wires given a resurrection to application specific integrated circuit (ASIC)-based accelerators. These…
In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of…
Gradient descent-based backpropagation training is widely used in many neural network systems. However, photonic implementation of such method is not straightforward mainly since having both the nonlinear activation function and its…
Stimulation of specific neurons expressing opsins in a targeted region to manipulate brain function has proved to be a powerful tool in neuroscience. However, the use of visible light for optogenetic stimulation is invasive due to low…