Related papers: Energy-efficient neural network inference with mic…
Exciton-polaritons have become an emerging platform for implementing non-Hermitian physics. The implementation commonly requires control of both the real and imaginary parts of the eigenmodes of the system. We present an experimental method…
Neuromorphic photonics promises sub-nanosecond latency, ultrawide bandwidth, and high parallelism, but practical scalability is constrained by fabrication tolerances, spectral alignment, and tuning energy. Here, we present a large-scale,…
Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We…
Computational hardware designed to mimic biological neural networks holds the promise to resolve the drastically growing global energy demand of artificial intelligence. A wide variety of hardware concepts have been proposed, and among…
We propose an efficient inverse design approach for multifunctional optical elements based on adaptive deep diffractive neural networks (a-D$^2$NNs). Specifically, we introduce a-D$^2$NNs and design two-layer diffractive devices that can…
Binary Neural Networks (BNNs) significantly reduce computational complexity and memory usage in machine and deep learning by representing weights and activations with just one bit. However, most existing training algorithms for BNNs rely on…
Deep learning has rapidly become a widespread tool in both scientific and commercial endeavors. Milestones of deep learning exceeding human performance have been achieved for a growing number of tasks over the past several years, across…
Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes inference, training…
With its unique parallel processing capability, optical neural network has shown low-power consumption in image recognition and speech processing. At present, the manufacturing technology of programmable photonic chip is not mature, and the…
It is a crucial issue to realize real-time piston correction in the area of sparse aperture imaging. This paper introduces an optical diffractive neural network-based piston sensing method, which can achieve light-speed sensing. By using…
Recent experiments in exciton-polariton systems have provided high-precision measurements of the value of the polariton-polariton interaction constant, which is a key parameter that governs the nonlinear dynamics of polariton condensates…
This work presents a machine learning approach to optimize the energy efficiency (EE) in a multi-cell wireless network. This optimization problem is non-convex and its global optimum is difficult to find. In the literature, either simple…
Microcavity polaritons are composite half-light half-matter quasi-particles, which have recently been demonstrated to exhibit rich physical properties, such as non-equilibrium Bose-Einstein condensation, parametric scattering and…
Recently, the deep neural network (derived from the artificial neural network) has attracted many researchers' attention by its outstanding performance. However, since this network requires high-performance GPUs and large storage, it is…
Recent advances in artificial intelligence, coupled with increasing data bandwidth requirements, in applications such as video processing and high-resolution sensing, have created a growing demand for high computational performance under…
Machine learning and AI have achieved remarkable advancements but at the cost of significant computational resources and energy consumption. This has created an urgent need for a novel, energy-efficient computational fabric to replace the…
Narrowband emission is crucial for next generation optoelectronic devices to satisfy demands for high color brilliance. Microcavities can narrow emission spectra of organic light-emitting diodes (OLEDs) through the creation of resonant…
The human brain performs tasks with an outstanding energy efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the other hand, have recently been shown to consume massive amounts…
The insensitivity of photons towards external magnetic fields forms one of the hardest barriers against efficient magneto-optical control, aiming at modulating the polarization state of light. However, there is even scarcer evidence of…
In this paper, we propose a low-power hardware for efficient deployment of binarized neural networks (BNNs) that have been trained for physiological datasets. BNNs constrain weights and feature-map to 1 bit, can pack in as many 1-bit…