Related papers: SINAPSE: A lightweight deep learning framework for…

Sparse regression on a library of candidate features has developed as the prime method to discover the partial differential equation underlying a spatio-temporal data-set. These features consist of higher order derivatives, limiting model…

Accurate identification of breast masses is crucial in diagnosing breast cancer; however, it can be challenging due to their small size and being camouflaged in surrounding normal glands. Worse still, it is also expensive in clinical…

Finding sparse solutions of underdetermined linear systems commonly requires the solving of L1 regularized least squares minimization problem, which is also known as the basis pursuit denoising (BPDN). They are computationally expensive…

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…

End user AI is trained on large server farms with data collected from the users. With ever increasing demand for IOT devices, there is a need for deep learning approaches that can be implemented (at the edge) in an energy efficient manner.…

This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enhancing generalization, but their interactions are poorly…

Plug-and-Play (PnP) algorithms are a class of iterative algorithms that address image inverse problems by combining a physical model and a deep neural network for regularization. Even if they produce impressive image restoration results,…

With large numbers of transients discovered by current and future imaging surveys, machine learning is increasingly applied to light curve and host galaxy properties to select events for follow-up. However, finding rare types of transients…

Spiking Neural Networks (SNNs) are highly energy-efficient during inference, making them particularly suitable for deployment on neuromorphic hardware. Their ability to process event-driven inputs, such as data from dynamic vision sensors…

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via…

Sparse adversarial attacks fool deep neural networks (DNNs) through minimal pixel perturbations, often regularized by the $\ell_0$ norm. Recent efforts have replaced this norm with a structural sparsity regularizer, such as the nuclear…

A deep convolutional neural network has been developed to denoise atomic-resolution TEM image datasets of nanoparticles acquired using direct electron counting detectors, for applications where the image signal is severely limited by shot…

We present a new procedure rooted in deep learning to construct science images from data cubes collected by astronomical instruments using HxRG detectors in low-flux regimes. It improves on the drawbacks of the conventional algorithms to…

A digital pulse shape discrimination system based on a programmable module NI-5772 has been established and tested with EJ-301 liquid scintillation detector. The module was operated by means of running programs developed in LabVIEW with the…

We present a novel approach for inspecting variable data prints (VDP) with an ultra-low false alarm rate (0.005%) and potential applicability to other real-world problems. The system is based on a comparison between two images: a reference…

Neural network hardware is considered an essential part of future edge devices. In this paper, we propose a binary-weight spiking neural network (BW-SNN) hardware architecture for low-power real-time object classification on edge platforms.…

Deep neural networks (DNNs) have been widely used to solve partial differential equations (PDEs) in recent years. In this work, a novel deep learning-based framework named Particle Weak-form based Neural Networks (ParticleWNN) is developed…

Denoising Diffusion Probabilistic Models (DDPMs) have shown success in robust 3D object detection tasks. Existing methods often rely on the score matching from 3D boxes or pre-trained diffusion priors. However, they typically require…

Spiking Neural Networks (SNNs) with a large number of weights and varied weight distribution can be difficult to implement in emerging in-memory computing hardware due to the limitations on crossbar size (implementing dot product), the…

Differentiating signals from the background in micrographs is a critical initial step for cryogenic electron microscopy (cryo-EM), yet it remains laborious due to low signal-to-noise ratio (SNR), the presence of contaminants and densely…