Related papers: Neural-network-based level-1 trigger upgrade for t…

This study addresses a key limitation in deep learning Automatic Modulation Classification (AMC) models, which perform well at high signal-to-noise ratios (SNRs) but degrade under noisy conditions due to conventional feature extraction…

This paper describes an online algorithm for enhancing monaural noisy speech. Firstly, a novel phase-corrected low-delay gammatone filterbank is derived for signal subband decomposition and resynthesis; the subband signals are then analyzed…

Despite the success of deep neural networks (DNNs) in image classification tasks, the human-level performance relies on massive training data with high-quality manual annotations, which are expensive and time-consuming to collect. There…

Autonomous radio self-triggering for extensive air showers must reject variable radio-frequency interference while preserving sensitivity to weak pulses and remaining compatible with station-level edge hardware. This work presents a hybrid…

DNN+NeuroSim is an integrated framework to benchmark compute-in-memory (CIM) accelerators for deep neural networks, with hierarchical design options from device-level, to circuit-level and up to algorithm-level. A python wrapper is…

For multi-stage recommenders in industry, a user request would first trigger a simple and efficient retriever module that selects and ranks a list of relevant items, then the recommender calls a slower but more sophisticated reranking model…

Fluorescence microscopy is a key driver to promote discoveries of biomedical research. However, with the limitation of microscope hardware and characteristics of the observed samples, the fluorescence microscopy images are susceptible to…

The memory demands of large-scale deep neural networks (DNNs) require synaptic weight values to be stored and updated in off-chip memory like dynamic random-access memory, which reduces energy efficiency and increases training time.…

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…

The classification of sleep stages is a pivotal aspect of diagnosing sleep disorders and evaluating sleep quality. However, the conventional manual scoring process, conducted by clinicians, is time-consuming and prone to human bias. Recent…

Networks are widely used in many fields for their powerful ability to provide vivid representations of relationships between variables. However, many of them may be corrupted by experimental noise or inappropriate network inference methods…

In cognitive radio systems, the ability to accurately detect primary user's signal is essential to secondary user in order to utilize idle licensed spectrum. Conventional energy detector is a good choice for blind signal detection, while it…

The backdoor attack poses a new security threat to deep neural networks. Existing backdoor often relies on visible universal trigger to make the backdoored model malfunction, which are not only usually visually suspicious to human but also…

A fast trigger system is being designed as a potential upgrade to VERITAS, or as the basis for a future array of imaging atmospheric-Cherenkov telescopes such as AGIS. The scientific goal is a reduction of the energy threshold by a factor…

Spiking neural networks have shown much promise as an energy-efficient alternative to artificial neural networks. However, understanding the impacts of sensor noises and input encodings on the network activity and performance remains…

Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective…

Reconstructing images using Computed Tomography (CT) in an industrial context leads to specific challenges that differ from those encountered in other areas, such as clinical CT. Indeed, non-destructive testing with industrial CT will often…

Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years. In this work, we theoretically study the importance of noise in the trajectories of gradient descent towards optimal…

In the upcoming years, with the upgrade of the LHC to higher luminosities, CMS will be subject to an increasing flux of particles, especially in its most forward region, at | \eta | > 1.6. To consolidate the muon spectrometer of CMS and…