Minimax Bayesian Neural Networks [PDF]
EntropyRobustness is an important issue in deep learning, and Bayesian neural networks (BNNs) provide means of robustness analysis, while the minimax method is a conservative choice in the classical Bayesian field.
Junping Hong, Ercan Engin Kuruoglu
doaj +4 more sources
Winsorization for Robust Bayesian Neural Networks [PDF]
Entropy, 2021 With the advent of big data and the popularity of black-box deep learning methods, it is imperative to address the robustness of neural networks to noise and outliers.
Somya Sharma, Snigdhansu Chatterjee
doaj +4 more sources
Bringing uncertainty quantification to the extreme-edge with memristor-based Bayesian neural networks [PDF]
Nature Communications, 2023 Safety-critical sensory applications, like medical diagnosis, demand accurate decisions from limited, noisy data. Bayesian neural networks excel at such tasks, offering predictive uncertainty assessment.
Djohan Bonnet +12 more
doaj +3 more sources
Bayesian Quantum Neural Networks
IEEE Access, 2022 The astounding acceleration in Artificial Intelligence and Quantum Computing advances naturally gives rise to a line of research, which unrolls the potential advantages of quantum computing on classical Machine Learning tasks, known as Quantum Machine ...
Nam Nguyen, Kwang-Cheng Chen
doaj +2 more sources
Bayesian neural networks for stock price forecasting before and during COVID-19 pandemic. [PDF]
PLoS ONE, 2021 Recently, there has been much attention in the use of machine learning methods, particularly deep learning for stock price prediction. A major limitation of conventional deep learning is uncertainty quantification in predictions which affect investor ...
Rohitash Chandra, Yixuan He
doaj +2 more sources
Layer wise Scaled Gaussian Priors for Markov Chain Monte Carlo Sampled deep Bayesian neural networks [PDF]
Frontiers in Artificial IntelligencePrevious work has demonstrated that initialization is very important for both fitting a neural network by gradient descent methods, as well as for Variational inference of Bayesian neural networks.
Devesh Jawla, John Kelleher
doaj +2 more sources
Bayesian Reasoning with Trained Neural Networks [PDF]
Entropy, 2021 We showed how to use trained neural networks to perform Bayesian reasoning in order to solve tasks outside their initial scope. Deep generative models provide prior knowledge, and classification/regression networks impose constraints.
Jakob Knollmüller, Torsten A. Enßlin
doaj +6 more sources
Two-dimensional materials-based probabilistic synapses and reconfigurable neurons for measuring inference uncertainty using Bayesian neural networks [PDF]
Nature Communications, 2022 Designing efficient Bayesian neural networks remains a challenge. Here, the authors use the cycle variation in the programming of the 2D memtransistors to achieve Gaussian random number generator-based synapses, and combine it with the complementary 2D ...
Amritanand Sebastian +6 more
doaj +2 more sources
On the relative expressiveness of Bayesian and neural networks
International Journal of Approximate Reasoning, 2019 A neural network computes a function. A central property of neural networks is that they are "universal approximators:" for a given continuous function, there exists a neural network that can approximate it arbitrarily well, given enough neurons (and some additional assumptions).
Adnan Darwiche, Arthur Choi
exaly +5 more sources
Approximate Bayesian neural networks in genomic prediction [PDF]
Genetics Selection Evolution, 2018 Background Genome-wide marker data are used both in phenotypic genome-wide association studies (GWAS) and genome-wide prediction (GWP). Typically, such studies include high-dimensional data with thousands to millions of single nucleotide polymorphisms ...
Patrik Waldmann
doaj +2 more sources