Related papers: A silicon photonics feed-forward neural network fo…

The de facto algorithm for training the back pass of a feedforward neural network is backpropagation (BP). The use of almost-everywhere differentiable activation functions made it efficient and effective to propagate the gradient backwards…

DSP (digital signal processing) has been widely applied in optical communication systems to mitigate signal distortions and has become one of the key technologies that have sustained data traffic growth over the past decade. However, the…

Neural networks are one of the disruptive computing concepts of our time. However, they fundamentally differ from classical, algorithmic computing in a number of fundamental aspects. These differences result in equally fundamental, severe…

Optics is an exciting route for the next generation of computing hardware for machine learning, promising several orders of magnitude enhancement in both computational speed and energy efficiency. However, to reach the full capacity of an…

Overparameterized neural networks often contain many removable neurons, yet what makes a neuron redundant remains poorly understood. Existing pruning criteria commonly rely on local quantities such as weight magnitude, activation strength,…

We present a deep neural network to reduce coherent noise in three-dimensional quantitative phase imaging. Inspired by the cycle generative adversarial network, the denoising network was trained to learn a transform between two image…

This work demonstrates a computational method for predicting the light propagation through a single multimode fiber using a deep neural network. The experiment for gathering training and testing data is performed with a digital micro-mirror…

Recent developments in photonics include efficient nanoscale optoelectronic components and novel methods for sub-wavelength light manipulation. Here, we explore the potential offered by such devices as a substrate for neuromorphic…

A fundamental road block for all-optical information processing is the difficulty in realizing a silicon optical transistor with the ability to provide optical gain, input output isolation and buffer action. In this work, we demonstrate an…

This paper proposes a non-data-driven deep neural network for spectral image recovery problems such as denoising, single hyperspectral image super-resolution, and compressive spectral imaging reconstruction. Unlike previous methods, the…

Diffractive neural networks hold great promise for applications requiring intensive computational processing. Considerable attention has focused on diffractive networks for either spatially coherent or spatially incoherent illumination.…

We present an approach to separating reflection from a single image. The approach uses a fully convolutional network trained end-to-end with losses that exploit low-level and high-level image information. Our loss function includes two…

Neural networks have proven effective for solving many difficult computational problems. Implementing complex neural networks in software is very computationally expensive. To explore the limits of information processing, it will be…

Reconfigurable photonic devices capable of routing the flow of light enable flexible integrated-optic circuits that are not hard-wired but can be externally controlled. Analogous to free-space spatial light modulators, we demonstrate…

We demonstrate that a deep neural network can significantly improve optical microscopy, enhancing its spatial resolution over a large field-of-view and depth-of-field. After its training, the only input to this network is an image acquired…

This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It…

Low-loss waveguides enable efficient light delivery in photonic circuits, which are essential for high-speed optical communications and scalable implementations of photonic quantum technologies. We study the effects of several fabrication…

A multitude of imaging and vision tasks have seen recently a major transformation by deep learning methods and in particular by the application of convolutional neural networks. These methods achieve impressive results, even for…

In recent years, artificial neural networks have achieved tremendous success for many vision-based tasks. However, this success remains within the paradigm of \emph{weak AI} where networks, among others, are specialized for just one given…

On-chip photonic networks have the potential to transmit and route information more efficiently than electronic circuits. Recently, a number of silicon-based optical devices including modulators, buffers, and wavelength converts have been…