Decision Support Systems for pavement and maintenance strategies have
traditionally been designed as silos led to local optimum systems. Moreover,
since big data usage didn't exist as result of Industry 4.0 as of today, DSSs
were not initially designed adaptive to the sources of uncertainties led to
rigid decisions. Motivated by the vulnerability of the road assets to the
climate phenomena, this paper takes a visionary step towards introducing a
Technology-Driven Adaptive Decision Support System for Integrated Pavement and
Maintenance activities called TDADSS-IPM. As part of such DSS, a bottom-up risk
assessment model is met via Bayesian Belief Networks (BBN) to realize the
actual condition of the Danish roads due to weather condition. Such model fills
the gaps in the knowledge domain and develops a platform that can be trained
over time, and applied in real-time to the actual event.

为应对气候现象引起的基础设施风险，提出了一种基于技术的自适应决策支持系统（TDADSS-IPM），采用贝叶斯信念网络（BBN）实现丹麦道路状况的实际情况。

基于技术驱动的路面养护一体化决策支持系统的研究：关注气候变化自适应风险评估框架

Towards a Technology-Driven Adaptive Decision Support System for  Integrated Pavement and Maintenance strategies (TDADSS-IPM): focus on risk  assessment framework for climate change adaptation

Attention-based neural networks have achieved state-of-the-art results on a
wide range of tasks. Most such models use deterministic attention while
stochastic attention is less explored due to the optimization difficulties or
complicated model design. This paper introduces Bayesian attention belief
networks, which construct a decoder network by modeling unnormalized attention
weights with a hierarchy of gamma distributions, and an encoder network by
stacking Weibull distributions with a deterministic-upward-stochastic-downward
structure to approximate the posterior. The resulting auto-encoding networks
can be optimized in a differentiable way with a variational lower bound. It is
simple to convert any models with deterministic attention, including pretrained
ones, to the proposed Bayesian attention belief networks. On a variety of
language understanding tasks, we show that our method outperforms deterministic
attention and state-of-the-art stochastic attention in accuracy, uncertainty
estimation, generalization across domains, and robustness to adversarial
attacks. We further demonstrate the general applicability of our method on
neural machine translation and visual question answering, showing great
potential of incorporating our method into various attention-related tasks.

本文提出贝叶斯关注置信网络并将其应用于多种任务中，相较于确定性和其他基于 stochastic attention 的模型，其在准确性、不确定性估计等指标上均更优。同时，这种方法还可用于调整其他基于 deterministic attention 的预训练模型，展现了广泛的应用潜力。

贝叶斯关注信念网络

Bayesian Attention Belief Networks

Neural networks predictions are unreliable when the input sample is out of
the training distribution or corrupted by noise. Being able to detect such
failures automatically is fundamental to integrate deep learning algorithms
into robotics. Current approaches for uncertainty estimation of neural networks
require changes to the network and optimization process, typically ignore prior
knowledge about the data, and tend to make over-simplifying assumptions which
underestimate uncertainty. To address these limitations, we propose a novel
framework for uncertainty estimation. Based on Bayesian belief networks and
Monte-Carlo sampling, our framework not only fully models the different sources
of prediction uncertainty, but also incorporates prior data information, e.g.
sensor noise. We show theoretically that this gives us the ability to capture
uncertainty better than existing methods. In addition, our framework has
several desirable properties: (i) it is agnostic to the network architecture
and task; (ii) it does not require changes in the optimization process; (iii)
it can be applied to already trained architectures. We thoroughly validate the
proposed framework through extensive experiments on both computer vision and
control tasks, where we outperform previous methods by up to 23% in accuracy.

提出了一种用基于贝叶斯信任网络和蒙特卡罗采样的方法来对神经网络进行不确定性估计，这个方法具有与神经网络结构和任务无关，不需要优化进程的更改，能够应用于已经训练好的结构，有效地提高了准确性。

深度学习不确定性估计的通用框架

A General Framework for Uncertainty Estimation in Deep Learning

Bayesian belief networks have grown to prominence because they provide
compact representations for many problems for which probabilistic inference is
appropriate, and there are algorithms to exploit this compactness. The next
step is to allow compact representations of the conditional probabilities of a
variable given its parents. In this paper we present such a representation that
exploits contextual independence in terms of parent contexts; which variables
act as parents may depend on the value of other variables. The internal
representation is in terms of contextual factors (confactors) that is simply a
pair of a context and a table. The algorithm, contextual variable elimination,
is based on the standard variable elimination algorithm that eliminates the
non-query variables in turn, but when eliminating a variable, the tables that
need to be multiplied can depend on the context. This algorithm reduces to
standard variable elimination when there is no contextual independence
structure to exploit. We show how this can be much more efficient than variable
elimination when there is structure to exploit. We explain why this new method
can exploit more structure than previous methods for structured belief network
inference and an analogous algorithm that uses trees.

本文介绍了一种新的表达条件概率的方式，利用了父亲背景的上下文无关性，提出了一种基于内部表现的算法。该算法可以更高效地利用在结构化信任网络中。