Large models for time series and spatio-temporal data: A survey and outlook
Temporal data, notably time series and spatio-temporal data, are prevalent in real-world
applications. They capture dynamic system measurements and are produced in vast …
applications. They capture dynamic system measurements and are produced in vast …
Liquid structural state-space models
A proper parametrization of state transition matrices of linear state-space models (SSMs)
followed by standard nonlinearities enables them to efficiently learn representations from …
followed by standard nonlinearities enables them to efficiently learn representations from …
[HTML][HTML] SNSVM: SqueezeNet-guided SVM for breast cancer diagnosis
Breast cancer is a major public health concern that affects women worldwide. It is a leading
cause of cancer-related deaths among women, and early detection is crucial for successful …
cause of cancer-related deaths among women, and early detection is crucial for successful …
Sequence modeling with multiresolution convolutional memory
Efficiently capturing the long-range patterns in sequential data sources salient to a given
task—such as classification and generative modeling—poses a fundamental challenge …
task—such as classification and generative modeling—poses a fundamental challenge …
[HTML][HTML] COVID-based controller: Enhancing automotive safety with a neuroadaptive beta-function optimization for anti-lock braking systems
Controlling wheel slip during braking in vehicle tires is a challenging task due to the
complex behavior and highly nonlinear dynamics involved. Uncertainties arising from …
complex behavior and highly nonlinear dynamics involved. Uncertainties arising from …
EEG-CDILNet: a lightweight and accurate CNN network using circular dilated convolution for motor imagery classification
T Liang, X Yu, X Liu, H Wang, X Liu… - Journal of Neural …, 2023 - iopscience.iop.org
Objective. The combination of the motor imagery (MI) electroencephalography (EEG) signals
and deep learning-based methods is an effective way to improve MI classification accuracy …
and deep learning-based methods is an effective way to improve MI classification accuracy …
Stable convolutional neural network for economy applications
A convolutional neural network does not require to be stable when it is used for economy
applications being related with the offline learning. Nevertheless, a convolutional neural …
applications being related with the offline learning. Nevertheless, a convolutional neural …
Capturing word positions does help: A multi-element hypergraph gated attention network for document classification
Y **, W Yin, H Wang, F He - Expert Systems with Applications, 2024 - Elsevier
Over the last few years, graph-based methods have manifested a significant enhancement
in document mining applications such as spam detection, news recommendation, and legal …
in document mining applications such as spam detection, news recommendation, and legal …
Feature fusion-based fiber-optic distributed acoustic sensing signal identification method
X Wang, C Wang, F Zhang, S Jiang… - Measurement …, 2023 - iopscience.iop.org
Fiber-optic distributed acoustic sensing (DAS) systems based on phase-sensitive optical
time-domain reflection technology have been widely used for perimeter security and oil and …
time-domain reflection technology have been widely used for perimeter security and oil and …
Spherical and Hyperbolic Toric Topology-Based Codes On Graph Embedding for Ising MRF Models: Classical and Quantum Topology Machine Learning
V Usatyuk, S Egorov, D Sapozhnikov - arxiv preprint arxiv:2307.15778, 2023 - arxiv.org
The paper introduces the application of information geometry to describe the ground states
of Ising models. This is achieved by utilizing parity-check matrices of cyclic and quasi-cyclic …
of Ising models. This is achieved by utilizing parity-check matrices of cyclic and quasi-cyclic …