Related papers: Application of multilayer perceptron with data aug…
Deep Learning (DL) methods have emerged as one of the most powerful tools for functional approximation and prediction. While the representation properties of DL have been well studied, uncertainty quantification remains challenging and…
In the Machine Learning research community, there is a consensus regarding the relationship between model complexity and the required amount of data and computation power. In real world applications, these computational requirements are not…
Mixed sample data augmentation strategies are actively used when training deep neural networks (DNNs). Recent studies suggest that they are effective at various tasks. However, the impact of mixed sample data augmentation on model…
As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in…
Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. However, they are often overconfident in their predictions, which leads to inaccurate and miscalibrated…
Accurate estimation of nuclear masses and their prediction beyond the experimentally explored domains of the nuclear landscape are crucial to an understanding of the fundamental origin of nuclear properties and to many applications of…
The paper discusses the capabilities of multilayer perceptron neural networks implementing metric recognition methods, for which the values of the weights are calculated analytically by formulas. Comparative experiments in training a neural…
Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…
In this study, we investigate how the updating of weights during forward operation and the computation of gradients during backpropagation impact the optimization process, training procedure, and overall performance of the neural network,…
Data augmentation is widely used to mitigate data bias in the training dataset. However, data augmentation exposes machine learning models to privacy attacks, such as membership inference attacks. In this paper, we propose an effective…
Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection.…
We measure the influence of image augmentations and training dataset size when training a deep neural network to classify galaxy morphology. Data augmentation is an integral step when training machine learning models and often astronomers…
Given the importance of nuclear mass predictions, numerous models have been developed to extrapolate the measured data into unknown regions. While neural networks -- the core of modern artificial intelligence -- have been recently suggested…
Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other…
We implement machine learning algorithms to nuclear data. These algorithms are purely data driven and generate models that are capable to capture intricate trends. Gradient boosted trees algorithm is employed to generate a trained model…
The Bayesian machine learning is a promising tool for the evaluation of nuclear fission data but its potential capability has not been fully realized. We attempt to optimize the performances of the multilayer Bayesian neural networks for…
In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The idea here is to…
Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the labeled data of many…
Protein solubility plays a critical role in improving production yield of recombinant proteins in biocatalyst and pharmaceutical field. To some extent, protein solubility can represent the function and activity of biocatalysts which are…
Deep neural networks have been exhibiting splendid accuracies in many of visual pattern classification problems. Many of the state-of-the-art methods employ a technique known as data augmentation at the training stage. This paper addresses…