Classification accuracy is a statistic that describes a classification model's performance by dividing the number of correct predictions by the total number of predictions. It is simple to compute and comprehend, making it the most often used statistic for assessing classifier models. But not in every scenario accuracy score is to be considered the best metric to evaluate the model. In this article, we will discuss the reasons not to believe in the accuracy performance parameter completely. Following are the topics to be covered.

In a recent study posted to Preprints with The Lancet*, researchers developed a machine learning approach to identify patients with long coronavirus disease (COVID). The post-acute sequelae of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection are called long COVID. In the present study, researchers aimed to generate a robust clinical definition for long COVID using data related to long COVID patients. The team utilized data obtained from electronic health records that were integrated and harmonized in the secure N3C Data Enclave. This allowed the team to identify unique patterns and clinical characteristics among COVID-19-infected patients.

If it can reduce false positives while still catching the real positives, that seems like a benefit,

Pull-based development has enabled numerous volunteers to contribute to open-source projects with fewer barriers. Nevertheless, a considerable amount of pull requests (PRs) with valid contributions are abandoned by their contributors, wasting the effort and time put in by both the contributors and maintainers. To better understand the underlying dynamics of contributor-abandoned PRs, we conduct a mixed-methods study using both quantitative and qualitative methods. We curate a dataset consisting of 265,325 PRs including 4,450 abandoned ones from ten popular and mature GitHub projects and measure 16 features characterizing PRs, contributors, review processes, and projects. Using statistical and machine learning techniques, we find that complex PRs, novice contributors, and lengthy reviews have a higher probability of abandonment and the rate of PR abandonment fluctuates alongside the projects' maturity or workload. To identify why contributors abandon their PRs, we also manually examine a random sample of 354 abandoned PRs. We observe that the most frequent abandonment reasons are related to the obstacles faced by contributors, followed by the hurdles imposed by maintainers during the review process. Finally, we survey the top core maintainers of the studied projects to understand their perspectives on dealing with PR abandonment and on our findings.

With his professed concern about fake accounts on Twitter, Elon Musk appears to be grasping at legal straws in an attempt to back out of his commitment to buy the social networking company for $54.20 a share, or at least to pay less for it. But his gambit has shined a light on a real scourge of online companies and their users. Counting the autonomous accounts that mimic real people is just as slippery as valuing companies. A 2020 study by Adrian Rauchfleisch and Jonas Kaiser looking at thousands of Twitter accounts, including hundreds of verified politicians as well as "obvious" bots, found Botometer, the industry-standard learning algorithm trained to calculate the likelihood an account is a bot, yields imprecise scores leading to both false negatives and false positives.

Poisoning attacks are a category of adversarial machine learning threats in which an adversary attempts to subvert the outcome of the machine learning systems by injecting crafted data into training data set, thus increasing the machine learning model's test error. The adversary can tamper with the data feature space, data labels, or both, each leading to a different attack strategy with different strengths. Various detection approaches have recently emerged, each focusing on one attack strategy. The Achilles heel of many of these detection approaches is their dependence on having access to a clean, untampered data set. In this paper, we propose CAE, a Classification Auto-Encoder based detector against diverse poisoned data. CAE can detect all forms of poisoning attacks using a combination of reconstruction and classification errors without having any prior knowledge of the attack strategy. We show that an enhanced version of CAE (called CAE+) does not have to employ a clean data set to train the defense model. Our experimental results on three real datasets MNIST, Fashion-MNIST and CIFAR demonstrate that our proposed method can maintain its functionality under up to 30% contaminated data and help the defended SVM classifier to regain its best accuracy.

Hierarchical multi-label classification (HMC) has drawn increasing attention in the past few decades. It is applicable when hierarchical relationships among classes are available and need to be incorporated along with the multi-label classification whereby each object is assigned to one or more classes. There are two key challenges in HMC: i) optimizing the classification accuracy, and meanwhile ii) ensuring the given class hierarchy. To address these challenges, in this article, we introduce a new statistic called the multidimensional local precision rate (mLPR) for each object in each class. We show that classification decisions made by simply sorting objects across classes in descending order of their true mLPRs can, in theory, ensure the class hierarchy and lead to the maximization of CATCH, an objective function we introduce that is related to the area under a hit curve. This approach is the first of its kind that handles both challenges in one objective function without additional constraints, thanks to the desirable statistical properties of CATCH and mLPR. In practice, however, true mLPRs are not available. In response, we introduce HierRank, a new algorithm that maximizes an empirical version of CATCH using estimated mLPRs while respecting the hierarchy. The performance of this approach was evaluated on a synthetic data set and two real data sets; ours was found to be superior to several comparison methods on evaluation criteria based on metrics such as precision, recall, and $F_1$ score.

Discourse cohesion facilitates text comprehension and helps the reader form a coherent narrative. In this study, we aim to computationally analyze the discourse cohesion in scientific scholarly texts using multilayer network representation and quantify the writing quality of the document. Exploiting the hierarchical structure of scientific scholarly texts, we design section-level and document-level metrics to assess the extent of lexical cohesion in text. We use a publicly available dataset along with a curated set of contrasting examples to validate the proposed metrics by comparing them against select indices computed using existing cohesion analysis tools. We observe that the proposed metrics correlate as expected with the existing cohesion indices. We also present an analytical framework, CHIAA (CHeck It Again, Author), to provide pointers to the author for potential improvements in the manuscript with the help of the section-level and document-level metrics. The proposed CHIAA framework furnishes a clear and precise prescription to the author for improving writing by localizing regions in text with cohesion gaps. We demonstrate the efficacy of CHIAA framework using succinct examples from cohesion-deficient text excerpts in the experimental dataset.

Causal inference can estimate causal effects, but unless data are collected experimentally, statistical analyses must rely on pre-specified causal models. Causal discovery algorithms are empirical methods for constructing such causal models from data. Several asymptotically correct methods already exist, but they generally struggle on smaller samples. Moreover, most methods focus on very sparse causal models, which may not always be a realistic representation of real-life data generating mechanisms. Finally, while causal relationships suggested by the methods often hold true, their claims about causal non-relatedness have high error rates. This non-conservative error tradeoff is not ideal for observational sciences, where the resulting model is directly used to inform causal inference: A causal model with many missing causal relations entails too strong assumptions and may lead to biased effect estimates. We propose a new causal discovery method that addresses these three shortcomings: Supervised learning discovery (SLdisco). SLdisco uses supervised machine learning to obtain a mapping from observational data to equivalence classes of causal models. We evaluate SLdisco in a large simulation study based on Gaussian data and we consider several choices of model size and sample size. We find that SLdisco is more conservative, only moderately less informative and less sensitive towards sample size than existing procedures. We furthermore provide a real epidemiological data application. We use random subsampling to investigate real data performance on small samples and again find that SLdisco is less sensitive towards sample size and hence seems to better utilize the information available in small datasets.

Tensorflow is an open-source end-to-end machine learning framework that makes it easy to train and deploy the model. It consists of two words - tensor and flow. A tensor is a vector or a multidimensional array that is a standard way of representing the data in deep learning models. Flow implies how the data moves through a graph by undergoing the operations called nodes. It is used for numerical computation and large-scale machine learning by bundling various algorithms together.