25 papers · ranked by Valyu relevance
Da Fan, David John Gagne, Steven J. Greybush, Eugene E. Clothiaux + 2 more
This study evaluated the probability and uncertainty forecasts of five recently proposed Bayesian deep learning methods relative to a deterministic residual neural network (ResNet) baseline for 0-1 h convective initiation (CI) nowcasting using GOES-16 satellite infrared observations. Uncertainty was assessed by how…
Hippolyt Ritter, Theofanis Karaletsos
We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro. Our leading design principle is to cleanly separate architecture, prior, inference and likelihood specification, allowing for a flexible workflow where users can quickly iterate over combinations of these components. In contrast to…
Melika Baghooee, Quentin Geissmann
Although visual features have been the cornerstone of insect recognition, morphological traits are often overlooked by modern “scale-invariant” deep learning-based methods. One such trait is absolute body size, which is commonly used by entomologists to describe species. We propose a novel approach that integrates…
Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo
Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying priors and approximate posterior distributions over neural network weights. Specifying meaningful weight priors is a challenging problem, particularly for scaling variational inference to deeper architectures involving high…
Nicholas Kuhn, Arvid Weyrauch, Lars Helge Heyen, Streit + 4 more
Bayesian neural networks (BNNs) are a useful tool for uncertainty quantification, but require substantially more computational resources than conventional neural networks. For non-Bayesian networks, the Lottery Ticket Hypothesis (LTH) posits the existence of sparse subnetworks that can train to the same or even…
Shangqi Gao, Xiahai Zhuang
Modeling statistics of image priors is useful for image super-resolution, but little attention has been paid from the massive works of deep learning-based methods. In this work, we propose a Bayesian image restoration framework, where natural image statistics are modeled with the combination of smoothness and sparsity…
Oscar Chang, Yuling Yao, David Williams-King, Hod Lipson
Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as "programming overhead." MC dropout [1] is popular because it sidesteps these…
Aryan Mobiny, Aditi Singh, Hien Van Nguyen
Knowing when a machine learning system is not confident about its prediction is crucial in medical domains where safety is critical. Ideally, a machine learning algorithm should make a prediction only when it is highly certain about its competency, and refer the case to physicians otherwise. In this paper, we…
Moule Lin, Shuhao Guan, Weipeng Jing, Goetz Botterweck + 1 more
'Andrea Patane'] While offering a principled framework for uncertainty quantification in deep learning, the employment of Bayesian Neural Networks (BNNs) is still constrained by their increased computational requirements and the convergence difficulties when training very deep, state-of-the-art architectures. In this…
Filippo Bargagna, Lisa Anita De Santi, Nicola Martini, Dario Genovesi + 6 more
'Dario Genovesi' 'Brunella Favilli' 'Giuseppe Vergaro' 'Michele Emdin' 'Assuero Giorgetti' 'Vincenzo Positano' 'Maria Filomena Santarelli'] Deep neural networks (DNNs) have already impacted the field of medicine in data analysis, classification, and image processing. Unfortunately, their performance is drastically…
Christian Leibig, Vaneeda Allken, Philipp Berens, Siegfried Wahl
Deep learning (DL) has revolutionized the field of computer vision and image processing. In medical imaging, algorithmic solutions based on DL have been shown to achieve high performance on tasks that previously required medical experts. However, DL-based solutions for disease detection have been proposed without…
Jennifer Vandoni, Sylvie Le Hégarat-Mascle, Emanuel Aldea
The main objective of this work is to study the applicability of ensemble methods in the context of deep learning with limited amounts of labeled data. We exploit an ensemble of neural networks derived using Monte Carlo dropout, along with an ensemble of SVM classifiers which owes its effectiveness to the hand-crafted…
Kevin Linka, Gerhard A Holzapfel, Ellen Kuhl
Understanding uncertainty is critical, especially when data are sparse and variations are large. Bayesian neural networks offer a powerful strategy to build predictable models from sparse data, and inherently quantify both, aleatoric uncertainties of the data and epistemic uncertainties of the model. Yet, classical…
Djohan Bonnet, Tifenn Hirtzlin, Atreya Majumdar, Thomas Dalgaty + 9 more
'Eduardo Esmanhotto' 'Valentina Meli' 'Niccolo Castellani' 'Simon Martin' 'Jean-François Nodin' 'Guillaume Bourgeois' 'Jean-Michel Portal' 'Damien Querlioz' 'Elisa Vianello'] Safety-critical sensory applications, like medical diagnosis, demand accurate decisions from limited, noisy data. Bayesian neural networks excel…
Hao Yin, Kai Zhang, Yu Lu, Yunfen Chang + 5 more
Highlights What are the main findings?1. A Bayesian CNN framework is proposed for imbalanced infrasound signal classification without the need for data augmentation. 2. The custom 4Conv3Fc architecture, trained via Bayesian inference, achieves a classification accuracy of 99.14%. 3. The framework is model-agnostic and…
Giacomo Deodato, Christopher Ball, Xian Zhang
Over the last decades, deep learning models have rapidly gained popularity for their ability to achieve state-of-the-art performances in different inference settings. Novel domains of application define a new set of requirements that transcend accurate predictions and depend on uncertainty measures. The aims of this…
Chenxi Sui, Ziyang Jiang, Genesis Higueros, David Carlson + 1 more
High-performance batteries are poised for electrification of vehicles and therefore mitigate greenhouse gas emissions, which, in turn, promote a sustainable future. However, the design of optimized batteries is challenging due to the nonlinear governing physics and electrochemistry. Recent advancements have…
Jan Steinbrener, Konstantin Posch, Jürgen Pilz
We present a novel approach for training deep neural networks in a Bayesian way. Compared to other Bayesian deep learning formulations, our approach allows for quantifying the uncertainty in model parameters while only adding very few additional parameters to be optimized. The proposed approach uses variational…
Patrick Kwabena Mensah, Mighty Abra Ayidzoe, Alex Akwasi Opoku, Kwabena Adu + 3 more
'Kwabena Adu' 'Benjamin Asubam Weyori' 'Isaac Kofi Nti' 'Peter Nimbe'] Capsule Networks have shown great promise in image recognition due to their ability to recognize the pose, texture, and deformation of objects and object parts. However, the majority of the existing capsule networks are deterministic with limited…
Benjamin Hoar, Weitong Zhang, Shuangning Xu, Rana Deeba + 3 more
For decades, employing cyclic voltammetry for mechanistic investigation demands manual inspection of voltammograms. Here we report a deep-learning-based algorithm that automatically analyzes cyclic voltammograms and designates a electrochemical probable mechanism among five of the most common ones in homogenous…
Lucian Chan, Geoffrey Hutchison, Garrett Morris
Generating low-energy molecular conformers is a key task for many areas of computational chemistry, molecular modeling and cheminformatics. Most current conformer generation methods primarily focus on generating geometrically diverse conformers rather than finding the most probable or energetically lowest minima. Here…
Lucian Chan, Geoffrey Hutchison, Garrett Morris
Generating low-energy molecular conformers is a key task for many areas of computational chemistry, molecular modeling and cheminformatics. Most current conformer generation methods primarily focus on generating geometrically diverse conformers rather than finding the most probable or energetically lowest minima. Here…
Yifan Wu, Aron Walsh, Alex Ganose
What is the minimum number of experiments, or calculations, required to find an optimal solution? Relevant chemical problems range from identifying a compound with target functionality within a given phase space to controlling materials synthesis and device fabrication conditions. A common feature in this application…
Authors not listed
Incorporating prior domain knowledge into Bayesian optimization (BO) remains difficult for statistical methods, which also typically suffer from limited interpretability. Large language models (LLMs) offer complementary strengths in reasoning and knowledge integration, but it remains unclear when and how they improve…
Sterling Baird, Jason R. Hall, Taylor D. Sparks
Would you rather search for a line inside a cube or a point inside a square? This type of solution degeneracy often exists in physics-based simulations and wet-lab experiments, but constraining these degeneracies is often unsupported or difficult to implement in many optimization packages, requiring additional time and…