AIMC Topic: Probability

Clear Filters Showing 161 to 170 of 438 articles

Probabilistic robustness estimates for feed-forward neural networks.

Neural networks : the official journal of the International Neural Network Society
Robustness of deep neural networks is a critical issue in practical applications. In the general case of feed-forward neural networks (including convolutional deep neural network architectures), under random noise attacks, we propose to study the pro...

Multi-periodicity of switched neural networks with time delays and periodic external inputs under stochastic disturbances.

Neural networks : the official journal of the International Neural Network Society
This paper presents new theoretical results on the multi-periodicity of recurrent neural networks with time delays evoked by periodic inputs under stochastic disturbances and state-dependent switching. Based on the geometric properties of activation ...

Identification and evaluation of maintenance error in catalyst replacement using the HEART technique under a fuzzy environment.

International journal of occupational safety and ergonomics : JOSE
. A necessity for this study was felt in the catalyst replacement process as a maintenance operation, because some fatal incidents have occurred due to human error in process industries during catalyst replacement operation. Identification and evalua...

Distant metastasis time to event analysis with CNNs in independent head and neck cancer cohorts.

Scientific reports
Deep learning models based on medical images play an increasingly important role for cancer outcome prediction. The standard approach involves usage of convolutional neural networks (CNNs) to automatically extract relevant features from the patient's...

Empirical strategy for stretching probability distribution in neural-network-based regression.

Neural networks : the official journal of the International Neural Network Society
In regression analysis under artificial neural networks, the prediction performance depends on determining the appropriate weights between layers. As randomly initialized weights are updated during back-propagation using the gradient descent procedur...

Personalized prediction of early childhood asthma persistence: A machine learning approach.

PloS one
Early childhood asthma diagnosis is common; however, many children diagnosed before age 5 experience symptom resolution and it remains difficult to identify individuals whose symptoms will persist. Our objective was to develop machine learning models...

Universal probabilistic programming offers a powerful approach to statistical phylogenetics.

Communications biology
Statistical phylogenetic analysis currently relies on complex, dedicated software packages, making it difficult for evolutionary biologists to explore new models and inference strategies. Recent years have seen more generic solutions based on probabi...

Fast convergence rates of deep neural networks for classification.

Neural networks : the official journal of the International Neural Network Society
We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smoot...

Modeling the predictive potential of extralinguistic context with script knowledge: The case of fragments.

PloS one
We describe a novel approach to estimating the predictability of utterances given extralinguistic context in psycholinguistic research. Predictability effects on language production and comprehension are widely attested, but so far predictability has...

Ensemble machine learning prediction and variable importance analysis of 5-year mortality after cardiac valve and CABG operations.

Scientific reports
Despite having a similar post-operative complication profile, cardiac valve operations are associated with a higher mortality rate compared to coronary artery bypass grafting (CABG) operations. For long-term mortality, few predictors are known. In th...