Related papers: L2ight: Enabling On-Chip Learning for Optical Neur…

A coupled spintronic oscillator array has been considered attractive for neuromorphic computing applications. Experimental reports have shown the nano-constriction geometry to be a relatively easier-to-fabricate platform for implementing…

In an attempt to follow biological information representation and organization principles, the field of neuromorphic engineering is usually approached bottom-up, from the biophysical models to large-scale integration in silico. While ideal…

Integrated photonic neural networks (PNNs) are at the forefront of AI computing, leveraging on light's unique properties, such as large bandwidth, low latency, and potentially low power consumption. Nevertheless, the integrated optical…

The ever-growing deep learning technologies are making revolutionary changes for modern life. However, conventional computing architectures are designed to process sequential and digital programs, being extremely burdened with performing…

The rapid scaling of deep neural networks comes at the cost of unsustainable power consumption. While optical neural networks offer an alternative, their capabilities remain constrained by the lack of efficient optical nonlinearities. To…

Lithium niobate-on-insulator (LNOI) is an emerging photonic platform that exhibits favorable material properties (such as low optical loss, strong nonlinearities, and stability) and enables large-scale integration with stronger optical…

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…

Onboard learning is a transformative approach in edge AI, enabling real-time data processing, decision-making, and adaptive model training directly on resource-constrained devices without relying on centralized servers. This paradigm is…

AI systems on edge devices require online continual learning -- adapting to non-stationary streams and unfamiliar classes without catastrophic forgetting -- under strict power constraints. We present CLP-SNN, a spiking neural network with a…

The rising demand for energy-efficient edge AI systems (e.g., mobile agents/robots) has increased the interest in neuromorphic computing, since it offers ultra-low power/energy AI computation through spiking neural network (SNN) algorithms…

Recent studies show that training deep neural networks (DNNs) with Lipschitz constraints are able to enhance adversarial robustness and other model properties such as stability. In this paper, we propose a layer-wise orthogonal training…

Compared with electrical neural networks, optical neural networks (ONNs) have the potentials to break the limit of the bandwidth and reduce the consumption of energy, and therefore draw much attention in recent years. By far, several types…

Light's ability to perform massive linear operations parallelly has recently inspired numerous demonstrations of optics-assisted artificial neural networks (ANN). However, a clear advantage of optics over purely digital ANN in a…

Distributed learning is widely used for training large models on large datasets by distributing parts of the model or dataset across multiple devices and aggregating the computed results for subsequent computations or parameter updates.…

Deep neural networks (DNNs) utilized recently are physically deployed with computational units (e.g., CPUs and GPUs). Such a design might lead to a heavy computational burden, significant latency, and intensive power consumption, which are…

Recent research efforts in optical computing have gravitated towards developing optical neural networks that aim to benefit from the processing speed and parallelism of optics/photonics in machine learning applications. Among these…

Emerging artificial intelligence applications across the domains of computer vision, natural language processing, graph processing, and sequence prediction increasingly rely on deep neural networks (DNNs). These DNNs require significant…

Optical neural networks (ONNs), implemented on an array of cascaded Mach-Zehnder interferometers (MZIs), have recently been proposed as a possible replacement for conventional deep learning hardware. They potentially offer higher energy…

Over the past decade, artificial intelligence (AI) has led to disruptive advancements in fundamental sciences and everyday technologies. Among various machine learning algorithms, deep neural networks have become instrumental in revealing…

A traditional artificial neural network (ANN) is normally trained slowly by a gradient descent algorithm, such as the backpropagation algorithm, since a large number of hyperparameters of the ANN need to be fine-tuned with many training…