An Interpretation Architecture for Deep Learning Models with the Application of COVID-19 Diagnosis

The Coronavirus disease 2019 (COVID-19) has become one of the threats to the world. Computed tomography (CT) is an informative tool for the diagnosis of COVID-19 patients. Many deep learning approaches on CT images have been proposed and brought promising performance. However, due to the high complexity and non-transparency of deep models, the explanation of the diagnosis process is challenging, making it hard to evaluate whether such approaches are reliable. In this paper, we propose a visual interpretation architecture for the explanation of the deep learning models and apply the architecture in COVID-19 diagnosis. Our architecture designs a comprehensive interpretation about the deep model from different perspectives, including the training trends, diagnostic performance, learned features, feature extractors, the hidden layers, the support regions for diagnostic decision, and etc. With the interpretation architecture, researchers can make a comparison and explanation about the classification performance, gain insight into what the deep model learned from images, and obtain the supports for diagnostic decisions. Our deep model achieves the diagnostic result of 94.75%, 93.22%, 96.69%, 97.27%, and 91.88% in the criteria of accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, which are 8.30%, 4.32%, 13.33%, 10.25%, and 6.19% higher than that of the compared traditional methods. The visualized features in 2-D and 3-D spaces provide the reasons for the superiority of our deep model. Our interpretation architecture would allow researchers to understand more about how and why deep models work, and can be used as interpretation solutions for any deep learning models based on convolutional neural network. It can also help deep learning methods to take a step forward in the clinical COVID-19 diagnosis field.     

The Challenges of Machine Learning and Their Economic Implications

The deployment of machine learning models is expected to bring several benefits. Nevertheless, as a result of the complexity of the ecosystem in which models are generally trained and deployed, this technology also raises concerns regarding its (1) interpretability, (2) fairness, (3) safety, and (4) privacy. These issues can have substantial economic implications because they may hinder the development and mass adoption of machine learning. In light of this, the purpose of this paper was to determine, from a positive economics point of view, whether the free use of machine learning models maximizes aggregate social welfare or, alternatively, regulations are required. In cases in which restrictions should be enacted, policies are proposed. The adaptation of current tort and anti-discrimination laws is found to guarantee an optimal level of interpretability and fairness. Additionally, existing market solutions appear to incentivize machine learning operators to equip models with a degree of security and privacy that maximizes aggregate social welfare. These findings are expected to be valuable to inform the design of efficient public policies.     

Why Do Big Data and Machine Learning Entail the Fractional Dynamics?

Fractional-order calculus is about the differentiation and integration of non-integer orders. Fractional calculus (FC) is based on fractional-order thinking (FOT) and has been shown to help us to understand complex systems better, improve the processing of complex signals, enhance the control of complex systems, increase the performance of optimization, and even extend the enabling of the potential for creativity. In this article, the authors discuss the fractional dynamics, FOT and rich fractional stochastic models. First, the use of fractional dynamics in big data analytics for quantifying big data variability stemming from the generation of complex systems is justified. Second, we show why fractional dynamics is needed in machine learning and optimal randomness when asking: “is there a more optimal way to optimize?”. Third, an optimal randomness case study for a stochastic configuration network (SCN) machine-learning method with heavy-tailed distributions is discussed. Finally, views on big data and (physics-informed) machine learning with fractional dynamics for future research are presented with concluding remarks.     

Detection of Anomalous Diffusion with Deep Residual Networks

Identification of the diffusion type of molecules in living cells is crucial to deduct their driving forces and hence to get insight into the characteristics of the cells. In this paper, deep residual networks have been used to classify the trajectories of molecules. We started from the well known ResNet architecture, developed for image classification, and carried out a series of numerical experiments to adapt it to detection of diffusion modes. We managed to find a model that has a better accuracy than the initial network, but contains only a small fraction of its parameters. The reduced size significantly shortened the training time of the model. Moreover, the resulting network has less tendency to overfitting and generalizes better to unseen data.     

几种吊钩中的力学问题探析

对吊装机械中使用的几种吊钩在吊装重物时的受力情况进行分析和比较,说明了各自的特点及其应用.     

Pooling设计在数控机床可靠性方面的应用

利用随机pooling设计的理论和方法,建立了数控机床可靠性筛选的定量分析数学模型,在统计分析观察工作时间段的基础上,可以筛选出可靠性差的数控机床,为数控机床的改进,产品质量的提高,提供理论依据.     

Choiceless polynomial time

Turing machines define polynomial time (PTime) on strings but cannot deal with structures like graphs directly, and there is no known, easily computable string encoding of isomorphism classes of structures. Is there a computation model whose machines do not distinguish between isomorphic structures and compute exactly PTime properties? This question can be recast as follows: Does there exist a logic that captures polynomial time (without presuming the presence of a linear order)? Earlier, one of us conjectured a negative answer. The problem motivated a quest for stronger and stronger PTime logics. All these logics avoid arbitrary choice. Here we attempt to capture the choiceless fragment of PTime. Our computation model is a version of abstract state machines (formerly called evolving algebras). The idea is to replace arbitrary choice with parallel execution. The resulting logic expresses all properties expressible in any other PTime logic in the literature. A more difficult theorem shows that the logic does not capture all of PTime.     

On weighting two criteria with a parameter in combinatorial optimization problems

Two criteria in a combinatorial problem are often combined in a weighted sum objective using a weighting parameter between 0 and 1. For special problem types, e.g., when one of the criteria is a bottleneck value, efficient algorithms are known that solve for a given value of the weighting parameter.     

Divergent Synthesis of Molecular Winch Prototypes

We report the synthesis of conceptually new prototypes of molecular winches with the ultimate aim to investigate the work performed by a single ruthenium-based molecular motor anchored on a surface by probing its ability to pull a load upon electrically-driven directional rotation. According to a technomimetic design, the motor was embedded in a winch structure, with a long flexible polyethylene glycol chain terminated by an azide hook to connect a variety of molecular loads. The structure of the motor was first derivatized by means of two sequential cross-coupling reactions involving a penta(4-halogenophenyl)cyclopentadienyl hydrotris(indazolyl)borate ruthenium(II) precursor and the resulting benzylamine derivative was next exploited as key intermediate in the divergent synthesis of a family of nanowinch prototypes. A one-pot method involving sequential peptide coupling and Cu-catalyzed azide-alkyne cycloaddition was developed to yield four loaded nanowinches, with load fragments encompassing triptycene, fullerene and porphyrin moieties.