教学课程资源库 更多>>

关键词： Computer science   Information technology   Scientific data   Software   Statistics  

摘要： After the great success of the Women's World Cup in 2019, several platforms have started identifying the reasons for gender inequality in European football. Even though these inequalities emerge from a variety of key aspects in the modern sport, we focused on the game and evaluated the main differential features of European male and female football players in match actions data under the assumption of finding significant differences and established patterns between genders. A methodology for unbiased feature extraction and objective analysis is presented based on data integration and machine learning explainability algorithms. Female (n0=1511) and male (n1=2703) data points were collected from event data and categorized by game period and player position. We set up a supervised classification pipeline to predict the gender of each player by looking at their actions in the game. The comparison methodology did not include any qualitative enrichment or subjective analysis to prevent biased data enhancement or gender-related processing. The pipeline included three representative binary classification models;A logic-based Decision Trees, a probabilistic Logistic Regression and a multilevel perceptron Neural Network. Each model tried to draw the differences between male and female data points, and we extracted the results using machine learning explainability methods to understand the underlying mechanics of the models implemented. The study was able to determine pivotal factors that differentiate each gender performance as well as disseminate unique patterns by gender involving more than one indicator. Data enhancement and critical variables analysis are essential next steps to support this framework and serve as a baseline for further studies and training developments.

关键词： Applied mathematics   Computer science  

摘要： A theoretical understanding of generalization remains an open problem for many machine learning models, including deep networks where overparameterization leads to better performance, contradicting the conventional wisdom from classical statistics. Here, we investigate generalization error for kernel regression, which, besides being a popular machine learning method, also describes certain infinitely overparameterized neural networks. We use techniques from statistical mechanics to derive an analytical expression for generalization error applicable to any kernel and data distribution. We present applications of our theory to real and synthetic datasets, and for many kernels including those that arise from training deep networks in the infinite-width limit. We elucidate an inductive bias of kernel regression to explain data with simple functions, characterize whether a kernel is compatible with a learning task, and show that more data may impair generalization when noisy or not expressible by the kernel, leading to non-monotonic learning curves with possibly many peaks. Canatar et al. propose a predictive theory of generalization in kernel regression applicable to real data. This theory explains various generalization phenomena observed in wide neural networks, which admit a kernel limit and generalize well despite being overparameterized.

关键词： computational science   computer science   reproducibility   validation   verification   uncertainty quantification  

关键词： Engineering education  

摘要： Based on the Technological Pedagogical and Content Knowledge (TPACK) framework (Mishra & Koehler, 2006) and the Schmidt et al. (2009) instrument which explore TPACK, this study examines a national sample of 1032 secondary teachers of computer science and measures their knowledge with respect to technology, pedagogy, content knowledge and the combination of each of these areas. Findings indicate that content knowledge and technology knowledge rating are high (average 4.38 and 4.16 respectively) and it seems that secondary teachers are less confident with their pedagogical content knowledge and their technological content knowledge (average 3.51 and 3.68 respectively). © 2021, CC BY.

关键词： Computer science   Policy  

摘要： Proliferating military artificial intelligence will leave the world less safe — so we must focus on ethics and global cooperation.

关键词： Computer science   Quantum information  

摘要： The use of quantum computing for machine learning is among the most exciting prospective applications of quantum technologies. However, machine learning tasks where data is provided can be considerably different than commonly studied computational tasks. In this work, we show that some problems that are classically hard to compute can be easily predicted by classical machines learning from data. Using rigorous prediction error bounds as a foundation, we develop a methodology for assessing potential quantum advantage in learning tasks. The bounds are tight asymptotically and empirically predictive for a wide range of learning models. These constructions explain numerical results showing that with the help of data, classical machine learning models can be competitive with quantum models even if they are tailored to quantum problems. We then propose a projected quantum model that provides a simple and rigorous quantum speed-up for a learning problem in the fault-tolerant regime. For near-term implementations, we demonstrate a significant prediction advantage over some classical models on engineered data sets designed to demonstrate a maximal quantum advantage in one of the largest numerical tests for gate-based quantum machine learning to date, up to 30 qubits. Expectations for quantum machine learning are high, but there is currently a lack of rigorous results on which scenarios would actually exhibit a quantum advantage. Here, the authors show how to tell, for a given dataset, whether a quantum model would give any prediction advantage over a classical one.

关键词： Social networking (online)  

摘要： Scientific collaboration networks can present different views of researchers’ interaction. The analysis of these networks allows research transparency focusing on the understanding of how science evolves in different contexts. In this article, we present a scientific collaboration network analysis using social network metrics as average degree, connected components, betweenness and closeness centralities applied to five Brazilian Computer Science graduate programs. An online artifact built upon the design science research paradigm, namely SCI-synergy, was developed to ease the analysis involving publication data available on the Digital Bibliography & Library Project (DBLP) from the graduate program members allied to the Federal University of Minas Gerais (UFMG), the State University of São Paulo (USP), the Federal University of Rio Grande do Norte (UFRN), the Federal University of Amazonas (UFAM), and the University of Brasília (UnB). The objective is to analyze the scientific collaboration network of each program focusing on the researchers’ collaboration to understand patterns considering intra- and inter-program relationships. The analysis covers two database updates of 2019 and 2021. Results show that intra-program relationships are not always bigger among the highest-ranked programs in CAPES. Nevertheless, UFMG presents a greater total of cooperation among the five programs indicating research leadership and good inter-program collaboration patterns. We advocate that the collaboration network analysis using an online artifact can be useful to understand patterns of all the Brazilian Computer Science graduate programs to discover new research perspectives to be improved, avoided or even applied to other contexts. © 2021, CC BY.

关键词： Machine learning   Computer science   Society   Technology   Sociology   Human behaviour  

摘要： To help humanity solve fundamental problems of cooperation, scientists need to reconceive artificial intelligence as deeply social. To help humanity solve fundamental problems of cooperation, scientists need to reconceive artificial intelligence as deeply social.

关键词： Computational biology and bioinformatics   Computer science   Software  

摘要： A new breed of notebooks is taking data visualization and collaborative functionality to the next level, with spreadsheet simplicity.

关键词： Computer science   Electrical and electronic engineering   Information technology   Learning algorithms  

摘要： While deep neural networks have surpassed human performance in multiple situations, they are prone to catastrophic forgetting: upon training a new task, they rapidly forget previously learned ones. Neuroscience studies, based on idealized tasks, suggest that in the brain, synapses overcome this issue by adjusting their plasticity depending on their past history. However, such "metaplastic" behaviors do not transfer directly to mitigate catastrophic forgetting in deep neural networks. In this work, we interpret the hidden weights used by binarized neural networks, a low-precision version of deep neural networks, as metaplastic variables, and modify their training technique to alleviate forgetting. Building on this idea, we propose and demonstrate experimentally, in situations of multitask and stream learning, a training technique that reduces catastrophic forgetting without needing previously presented data, nor formal boundaries between datasets and with performance approaching more mainstream techniques with task boundaries. We support our approach with a theoretical analysis on a tractable task. This work bridges computational neuroscience and deep learning, and presents significant assets for future embedded and neuromorphic systems, especially when using novel nanodevices featuring physics analogous to metaplasticity. Deep neural networks usually rapidly forget the previously learned tasks while training new ones. Laborieux et al. propose a method for training binarized neural networks inspired by neuronal metaplasticity that allows to avoid catastrophic forgetting and is relevant for neuromorphic applications.