中文
相关论文

相关论文: Learning noisy-OR Bayesian Networks with Max-Produ…

200 篇论文

This paper investigates two prominent probabilistic neural modeling paradigms: Bayesian Neural Networks (BNNs) and Mixture Density Networks (MDNs) for uncertainty-aware nonlinear regression. While BNNs incorporate epistemic uncertainty by…

统计计算 · 统计学 2025-10-30 Riddhi Pratim Ghosh , Ian Barnett

Matrix decomposition is a popular and fundamental approach in machine learning and data mining. It has been successfully applied into various fields. Most matrix decomposition methods focus on decomposing a data matrix from one single…

计算机视觉与模式识别 · 计算机科学 2017-12-12 Chihao Zhang , Shihua Zhang

Batch normalization (BN) is a popular and ubiquitous method in deep learning that has been shown to decrease training time and improve generalization performance of neural networks. Despite its success, BN is not theoretically well…

机器学习 · 计算机科学 2022-01-21 Susanna Lange , Kyle Helfrich , Qiang Ye

Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern deep learning. However, they generally struggle with underfitting at scale and parameter efficiency. On the…

We present two methods to reduce the complexity of Bayesian network (BN) classifiers. First, we introduce quantization-aware training using the straight-through gradient estimator to quantize the parameters of BNs to few bits. Second, we…

机器学习 · 计算机科学 2021-09-23 Wolfgang Roth , Günther Schindler , Holger Fröning , Franz Pernkopf

Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce overconfident predictions, and frequently lack the ability to…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Sarah Harkins Dayton , Hayden Everett , Ioannis Schizas , David L. Boothe , Vasileios Maroulas

Batch Normalization (BN) is a commonly used technique to accelerate and stabilize training of deep neural networks. Despite its empirical success, a full theoretical understanding of BN is yet to be developed. In this work, we analyze BN…

机器学习 · 计算机科学 2022-03-22 Tolga Ergen , Arda Sahiner , Batu Ozturkler , John Pauly , Morteza Mardani , Mert Pilanci

Max-Linear Bayesian Networks (MLBNs) provide a powerful framework for causal inference in extreme-value settings; we consider MLBNs with noise parameters with a given topology in terms of the max-plus algebra by taking its logarithm. Then,…

机器学习 · 统计学 2025-05-02 Mark Adams , Kamillo Ferry , Ruriko Yoshida

Mutual Information (MI) is a crucial measure for capturing dependencies between variables, but exact computation is challenging in high dimensions with intractable likelihoods, impacting accuracy and robustness. One idea is to use an…

机器学习 · 统计学 2025-03-13 Forough Fazeliasl , Michael Minyi Zhang , Bei Jiang , Linglong Kong

Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and…

机器学习 · 计算机科学 2021-11-12 Giuseppina Carannante , Dimah Dera , Ghulam Rasool , Nidhal C. Bouaynaya , Lyudmila Mihaylova

In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes. This requires approaches to effectively detect and resolve disturbances to ensure optimal…

机器学习 · 统计学 2021-02-05 Weike Sun , Antonio R. C. Paiva , Peng Xu , Anantha Sundaram , Richard D. Braatz

Despite their theoretical appealingness, Bayesian neural networks (BNNs) are left behind in real-world adoption, mainly due to persistent concerns on their scalability, accessibility, and reliability. In this work, we develop the…

机器学习 · 计算机科学 2022-10-14 Zhijie Deng , Jun Zhu

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…

机器学习 · 计算机科学 2025-05-26 Moule Lin , Shuhao Guan , Weipeng Jing , Goetz Botterweck , Andrea Patane

Artificial neural networks (ANNs) are powerful machine learning methods used in many modern applications such as facial recognition, machine translation, and cancer diagnostics. A common issue with ANNs is that they usually have millions or…

机器学习 · 统计学 2023-05-08 Lars Skaaret-Lund , Geir Storvik , Aliaksandr Hubin

The rapidly increasing computational demands for artificial intelligence (AI) have spurred the exploration of computing principles beyond conventional digital computers. Physical neural networks (PNNs) offer efficient neuromorphic…

Convolutional neural networks (CNNs) work well on large datasets. But labelled data is hard to collect, and in some applications larger amounts of data are not available. The problem then is how to use CNNs with small data -- as CNNs…

机器学习 · 统计学 2016-01-19 Yarin Gal , Zoubin Ghahramani

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

计算机视觉与模式识别 · 计算机科学 2023-02-13 Peng Cui , Yang Yue , Zhijie Deng , Jun Zhu

This research introduces a novel methodology for optimizing Bayesian Neural Networks (BNNs) by synergistically integrating them with traditional machine learning algorithms such as Random Forests (RF), Gradient Boosting (GB), and Support…

机器学习 · 计算机科学 2023-10-10 Peiwen Tan

Bayesian neural network models (BNN) have re-surged in recent years due to the advancement of scalable computations and its utility in solving complex prediction problems in a wide variety of applications. Despite the popularity and…

机器学习 · 统计学 2020-11-20 Shrijita Bhattacharya , Zihuan Liu , Tapabrata Maiti

In this work, we aim to enhance the system robustness of end-to-end automatic speech recognition (ASR) against adversarially-noisy speech examples. We focus on a rigorous and empirical "closed-model adversarial robustness" setting (e.g.,…

音频与语音处理 · 电气工程与系统科学 2022-02-18 Chao-Han Huck Yang , Zeeshan Ahmed , Yile Gu , Joseph Szurley , Roger Ren , Linda Liu , Andreas Stolcke , Ivan Bulyko