Related papers: SOUL: An Energy-Efficient Unsupervised Online Lear…
It is well known that the success of deep neural networks is greatly attributed to large-scale labeled datasets. However, it can be extremely time-consuming and laborious to collect sufficient high-quality labeled data in most practical…
Transformer neural networks require a large amount of labeled data to train effectively. Such data is often scarce in electroencephalography, as annotations made by medical experts are costly. This is why self-supervised training, using…
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and effective method self-ensemble label filtering (SELF) to…
Probabilistic security assessment and real-time dynamic security assessments (DSA) are promising to better handle the risks of system operations. The current methodologies of security assessments may require many time-domain simulations for…
Neural models have shown several state-of-the-art performances on Semantic Role Labeling (SRL). However, the neural models require an immense amount of semantic-role corpora and are thus not well suited for low-resource languages or…
Epileptic seizures are one of the most crucial neurological disorders, and their early diagnosis will help the clinicians to provide accurate treatment for the patients. The electroencephalogram (EEG) signals are widely used for epileptic…
Objective: Stroke is one of the leading causes of disabilities. One promising approach is to extend the rehabilitation with self-initiated robot-assisted movement therapy. To enable this, it is required to detect the patient's intention to…
The past few years have witnessed a remarkable advance in deep learning for EEG-based sleep stage classification (SSC). However, the success of these models is attributed to possessing a massive amount of labeled data for training, limiting…
Neonates are highly susceptible to seizures, often leading to short or long-term neurological impairments. However, clinical manifestations of neonatal seizures are subtle and often lead to misdiagnoses. This increases the risk of…
Data driven generative machine learning models have recently emerged as one of the most promising approaches for new materials discovery. While the generator models can generate millions of candidates, it is critical to train fast and…
With the increasing availability of data for Prognostics and Health Management (PHM), Deep Learning (DL) techniques are now the subject of considerable attention for this application, often achieving more accurate Remaining Useful Life…
In this paper, we revisit techniques for uncertainty estimation within deep neural networks and consolidate a suite of techniques to enhance their reliability. Our investigation reveals that an integrated application of diverse…
Electroencephalogram (EEG) monitoring and objective seizure identification is an essential clinical investigation for some patients with epilepsy. Accurate annotation is done through a time-consuming process by EEG specialists.…
Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primarily on data-centric or weight-based strategies frequently…
Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…
Large-scale scientific simulations generate massive datasets, posing challenges for storage and I/O. Traditional lossy compression struggles to advance more in balancing compression ratio, data quality, and adaptability to diverse…
Analytical models developed in offline settings with pre-prepared data are typically used to predict students' performance. However, when data are available over time, this learning method is not suitable anymore. Online learning is…
Residential buildings with the ability to monitor and control their net-load (sum of load and generation) can provide valuable flexibility to power grid operators. We present a novel multiclass nonintrusive load monitoring (NILM) approach…
Environmental Sound Classification (ESC) is a challenging field of research in non-speech audio processing. Most of current research in ESC focuses on designing deep models with special architectures tailored for specific audio datasets,…
Unsupervised time series clustering is a challenging problem with diverse industrial applications such as anomaly detection, bio-wearables, etc. These applications typically involve small, low-power devices on the edge that collect and…