AIMC Topic: Neural Networks, Computer

Clear Filters Showing 131 to 140 of 29771 articles

Mitigating data bias and ensuring reliable evaluation of AI models with shortcut hull learning.

Nature communications
Shortcut learning poses a significant challenge to both the interpretability and robustness of artificial intelligence, arising from dataset biases that lead models to exploit unintended correlations, or shortcuts, which undermine performance evaluat...

Stable recurrent dynamics in heterogeneous neuromorphic computing systems using excitatory and inhibitory plasticity.

Nature communications
Many neural computations emerge from self-sustained patterns of activity in recurrent neural circuits, which rely on balanced excitation and inhibition. Neuromorphic electronic circuits represent a promising approach for implementing the brain's comp...

Hybrid transfer learning and self-attention framework for robust MRI-based brain tumor classification.

Scientific reports
Brain tumors are a significant contributor to cancer-related deaths worldwide. Accurate and prompt detection is crucial to reduce mortality rates and improve patient survival prospects. Magnetic Resonance Imaging (MRI) is crucial for diagnosis, but m...

A novel feature extractor based on constrained cross network for detecting sleep state.

Scientific reports
With increasing awareness of healthy living and social pressure, more and more people have begun to pay attention to their sleep state. Most existing methods that utilize wrist-worn devices data for detection rely on heuristic algorithms or tradition...

Edaphic and meteorological parameters as determinants of radon exhalation and its environmental implication in Peruvian agroecosystems.

Scientific reports
Radon exhalation is a natural process by which atoms of the radioactive gas radon diffuse in the soil and then exhale to an indoor and/or outdoor environment. High radon concentration levels, possibly from high radon exhalation rate levels, can gener...

DeepECG-Net: a hybrid transformer-based deep learning model for real-time ECG anomaly detection.

Scientific reports
Real-time Electrocardiogram (ECG) anomaly detection is critical for accurate diagnosis and timely intervention in cardiac disorders. Existing models, such as CNNs and LSTMs, often struggle with long-range dependencies, generalization across multiple ...

Application of wings interferential patterns (WIPs) and deep learning (DL) to classify some Culex. spp (Culicidae) of medical or veterinary importance.

Scientific reports
In this paper, we test the possibility of using Wing Interference Patterns (WIPs) and deep learning (DL) for the identification of Culex mosquitoes species to evaluate the extent to which a generic method could be developed for surveying Dipteran ins...

Construction of intelligent gymnastics teaching model based on neural network and artificial intelligence.

Scientific reports
This study aims to develop intelligent gymnastics teaching model based on Artificial Neural Network (ANN). It addresses key issues in traditional gymnastics teaching, such as difficulty in quantifying the teaching process and lack of personalized gui...

An automatic classification of breast cancer using fuzzy scoring based ResNet CNN model.

Scientific reports
The expansion rate of medical data during the past ten years has rapidly expanded due to the vast fields. The automated disease diagnosis system is proposed using a deep learning (DL) algorithm, which automates and helps speed up the process efficien...

Deep learning based knowledge tracing in intelligent tutoring systems.

Scientific reports
The emergence of online education, e.g., intelligent tutoring system (ITS), complements or partially replaces conventional offline education, especially during the COVID-19 pandemic. Knowledge tracing (KT) plays a pivotal role in the intelligent tuto...