Related papers: Reconfigurable Silicon Photonics Extreme Learning …
Electronically reprogrammable photonic circuits based on phase-change chalcogenides present an avenue to resolve the von-Neumann bottleneck; however, implementation of such hybrid photonic-electronic processing has not achieved…
Automated experiments in scanning transmission electron microscopy (STEM) require rapid image segmentation to optimize data representation for human interpretation, decision-making, site-selective spectroscopies, and atomic manipulation.…
Electroencephalography (EEG) classification is a versatile and portable technique for building non-invasive Brain-computer Interfaces (BCI). However, the classifiers that decode cognitive states from EEG brain data perform poorly when…
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims to learn modality-invariant features from unlabeled cross-modality datasets and reduce the inter-modality gap. However, the existing methods lack…
In this work, we experimentally validate the dual use of a reconfigurable photonic integrated mesh as a neuromorphic accelerator, targeting signal equalization, and as a physical unclonable function offering authentication at the hardware…
Low-loss electron energy loss spectroscopy (EELS) has emerged as a technique of choice for exploring the localization of plasmonic phenomena at the nanometer level, necessitating analysis of physical behaviors from 3D spectral data sets.…
We design specific neural networks (NNs) for the identification of switching nonlinear systems in the state-space form, which explicitly model the switching behavior and address the inherent coupling between system parameters and switching…
This paper presents a novel fixation prediction and saliency modeling framework based on inter-image similarities and ensemble of Extreme Learning Machines (ELM). The proposed framework is inspired by two observations, 1) the contextual…
Scanning Electron Microscopy (SEM) is indispensable in modern materials science, enabling high-resolution imaging across a wide range of structural, chemical, and functional investigations. However, SEM imaging remains constrained by…
Recent developments have led to the possibility of embedding machine learning tools into experimental platforms to address key problems, including the characterization of the properties of quantum states. Leveraging on this, we implement a…
Explicit-electron force fields introduce electrons or electron pairs as semi-classical particles in force fields or empirical potentials, which are suitable for molecular dynamics simulations. Even though semi-classical electrons are a…
The new era of artificial intelligence demands large-scale ultrafast hardware for machine learning. Optical artificial neural networks process classical and quantum information at the speed of light, and are compatible with silicon…
Spiking neural networks (SNN) provide a new computational paradigm capable of highly parallelized, real-time processing. Photonic devices are ideal for the design of high-bandwidth, parallel architectures matching the SNN computational…
We propose a novel explicit dense 3D reconstruction approach that processes a set of images of a scene with sensor poses and calibrations and estimates a photo-real digital model. One of the key innovations is that the underlying volumetric…
Although current semi-supervised medical segmentation methods can achieve decent performance, they are still affected by the uncertainty in unlabeled data and model predictions, and there is currently a lack of effective strategies that can…
Read-only memory (ROM) provides deterministic access to predefined data mappings. Extending ROM concepts to the optical domain enables high-bandwidth, low-latency, and parallel memory access, but realizing compact and reconfigurable optical…
Photonic computing promises ultrafast and energy-efficient artificial intelligence. However, existing photonic neural networks (PNNs) remain functionally shallow and difficult to scale. Here we establish a theory-guided framework showing…
Most edge AI focuses on prediction tasks on resource-limited edge devices while the training is done at server machines. However, retraining or customizing a model is required at edge devices as the model is becoming outdated due to…
With the growing need for real-time processing on IoT devices, optimizing machine learning (ML) models' size, latency, and computational efficiency is essential. This paper investigates a pruning method for anomaly detection in…
Spiking Neural Networks (SNNs) as Machine Learning (ML) models have recently received a lot of attention as a potentially more energy-efficient alternative to conventional Artificial Neural Networks. The non-differentiability and sparsity…