Related papers: Programmable Photonic Extreme Learning Machines

Neural networks provide a powerful tool for applications from classification and regression to general purpose alternative computing. Photonics have the potential to provide enormous speed benefits over electronic and software networks,…

Emulator embedded neural networks, which are a type of physics informed neural network, leverage multi-fidelity data sources for efficient design exploration of aerospace engineering systems. Multiple realizations of the neural network…

Chalcogenide phase-change materials (PCMs) offer a promising approach to programmable photonics thanks to their nonvolatile, reversible phase transitions and high refractive index contrast. However, conventional designs are limited by…

Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train. We present techniques to scale MCMC based EBM training on continuous neural networks,…

Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image…

This paper explores the potential of extreme learning machine based supervised classification algorithm for land cover classification. In comparison to a backpropagation neural network, which requires setting of several user-defined…

Multi-plane light converter (MPLC) designs supporting hundreds of modes are attractive in high-throughput optical communications. These photonic structures typically comprise >10 phase masks in free space, with millions of independent…

Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive multi-sensory data analysis directly on edge intelligent…

The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices. To overcome this challenge, in this paper, we advocate the…

Photonic neural networks capable of rapid programming are indispensable to realize many functionalities. Phase change technology can provide nonvolatile programmability in photonic neural networks. Integrating direct laser writing technique…

We present Parametric Piecewise Linear Networks (PPLNs) for temporal vision inference. Motivated by the neuromorphic principles that regulate biological neural behaviors, PPLNs are ideal for processing data captured by event cameras, which…

While software implementations of neural networks have driven significant advances in computation, the von Neumann architecture imposes fundamental limitations on speed and energy efficiency. Neuromorphic networks, with structures inspired…

We develop an interpolation-based modeling framework for parameter-dependent partial differential equations arising in control, inverse problems, and uncertainty quantification. The solution is discretized in the physical domain using…

We propose advancing photonic in-memory computing through three-dimensional photonic-electronic integrated circuits using phase-change materials (PCM) and AlGaAs-CMOS technology. These circuits offer high precision (greater than 12 bits),…

In pseudo-labeling (PL), which is a type of semi-supervised learning, pseudo-labels are assigned based on the confidence scores provided by the classifier; therefore, accurate confidence is important for successful PL. In this study, we…

Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired knowledge. A major obstacle in this setting is catastrophic forgetting, where…

Deep energy-based models (EBMs) are very flexible in distribution parametrization but computationally challenging because of the intractable partition function. They are typically trained via maximum likelihood, using contrastive divergence…

Deep learning based approaches have achieved significant progresses in different tasks like classification, detection, segmentation, and so on. Ensemble learning is widely known to further improve performance by combining multiple…

Photonic chip design has seen significant advancements with the adoption of inverse design methodologies, offering flexibility and efficiency in optimizing device performance. However, the black-box nature of the optimization approaches,…

Neural networks have enabled applications in artificial intelligence through machine learning, and neuromorphic computing. Software implementations of neural networks on conventional computers that have separate memory and processor (and…