AIMC Topic: Normal Distribution

Clear Filters Showing 31 to 40 of 282 articles

Bidirectionally self-normalizing neural networks.

Neural networks : the official journal of the International Neural Network Society
The problem of vanishing and exploding gradients has been a long-standing obstacle that hinders the effective training of neural networks. Despite various tricks and techniques that have been employed to alleviate the problem in practice, there still...

Physiologically-Informed Gaussian Processes for Interpretable Modelling of Psycho-Physiological States.

IEEE journal of biomedical and health informatics
The widespread popularity of Machine Learning (ML) models in healthcare solutions has increased the demand for their interpretability and accountability. In this paper, we propose the Physiologically-Informed Gaussian Process (PhGP) classification mo...

Using Feature Engineering and Principal Component Analysis for Monitoring Spindle Speed Change Based on Kullback-Leibler Divergence with a Gaussian Mixture Model.

Sensors (Basel, Switzerland)
Machining is a crucial constituent of the manufacturing industry, which has begun to transition from precision machinery to smart machinery. Particularly, the introduction of artificial intelligence into computer numerically controlled (CNC) machine ...

Analysis on the inherent noise tolerance of feedforward network and one noise-resilient structure.

Neural networks : the official journal of the International Neural Network Society
In the past few decades, feedforward neural networks have gained much attraction in their hardware implementations. However, when we realize a neural network in analog circuits, the circuit-based model is sensitive to hardware nonidealities. The noni...

DyVGRNN: DYnamic mixture Variational Graph Recurrent Neural Networks.

Neural networks : the official journal of the International Neural Network Society
Although graph representation learning has been studied extensively in static graph settings, dynamic graphs are less investigated in this context. This paper proposes a novel integrated variational framework called DYnamic mixture Variational Graph ...

Adversarial feature hybrid framework for steganography with shifted window local loss.

Neural networks : the official journal of the International Neural Network Society
Image steganography is a long-standing image security problem that aims at hiding information in cover images. In recent years, the application of deep learning to steganography has the tendency to outperform traditional methods. However, the vigorou...

Regularizing transformers with deep probabilistic layers.

Neural networks : the official journal of the International Neural Network Society
Language models (LM) have grown non-stop in the last decade, from sequence-to-sequence architectures to attention-based Transformers. However, regularization is not deeply studied in those structures. In this work, we use a Gaussian Mixture Variation...

Dual parallel net: A novel deep learning model for rectal tumor segmentation via CNN and transformer with Gaussian Mixture prior.

Journal of biomedical informatics
Segmentation of rectal cancerous regions from Magnetic Resonance (MR) images can help doctor define the extent of the rectal cancer and judge the severity of rectal cancer, so rectal tumor segmentation is crucial to improve the accuracy of rectal can...

Machine learning for better prediction of seepage flow through embankment dams: Gaussian process regression versus SVR and RVM.

Environmental science and pollution research international
In the present study, three machine learning methods were applied for predicting seepage flow through embankment dams, namely (i) support vector regression (SVR), relevance vector machine (RVM), and Gaussian process regression (GPR). The three models...

Relating local connectivity and global dynamics in recurrent excitatory-inhibitory networks.

PLoS computational biology
How the connectivity of cortical networks determines the neural dynamics and the resulting computations is one of the key questions in neuroscience. Previous works have pursued two complementary approaches to quantify the structure in connectivity. O...