Scientific Computing Meets Machine Learning and Life Sciences

《科学计算遇见机器学习与生命科学》工作坊将于2019年10月7日至10月9日在德克萨斯州拉伯克市得克萨斯理工大学校园举行。这次工作坊将汇集来自数学、统计学、计算机科学、机器学习、数据科学和生命科学的顶尖专家和早期职业研究人员，报告科学计算中的尖端和最先进的计算算法，并确定机器学习和生命科学中的计算和统计挑战和开放问题。此外，讲习班将为国际和多样化的研究人员小组提供一个论坛，以促进交流，促进新的协作互动，并发起联合研究项目，以解决机器学习和生命科学中的公开和新出现的问题以及计算和统计方面的挑战。为期三天的研讨会将包括演讲、海报和小组讨论，以促进思想的密集交流和促进富有成效的互动。该奖项支持研究人员和研究生的出席，优先考虑研究生、博士后学者、早期职业调查人员、代表性不足群体的成员，以及没有其他联邦支持的研究人员。科学计算在许多科学和工程领域，如生物医学成像、基因组学、蛋白质组学、系统发育学、计算机视觉和精密医学中，是一个日益重要的工具，允许探索不符合理论或实验研究的生物数据和系统。机器学习是一种自动建立分析模型的数据分析方法。它是人工智能的一个分支，基于这样的想法：系统可以从数据中学习，识别模式，并在最少的人工干预下做出决策。大数据时代的到来将机器学习推向了前沿，并在近年来激发了人们对机器学习的广泛兴趣。生命科学领域通过对生物学的深入理解和数学技术之间的协同作用而取得进展，特别是从计算数学、概率和统计学的角度。尽管如此，生物学家还是被产生的数据量和数据管理所需的新方法淹没了。需要量化理论来帮助解释观察结果并将其与背景联系起来。近年来，机器学习的科学计算领域出现了与生命科学相关的各种新挑战，例如为疾病检测、药物再利用、毒性预测、电子健康记录分析、语言翻译等开发预测模型。这些问题和许多其他公开问题将在参加研讨会的不同科学家群体中讨论。更多信息可在http://www.math.ttu.edu/scmlls2019/.This获得，该奖项反映了国家科学基金会的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The workshop "Scientific Computing meets Machine Learning and Life Sciences" will be held on the campus of Texas Tech University in Lubbock, TX, from October 7 through October 9, 2019. This workshop will bring together leading experts and early career researchers from mathematics, statistics, computer science, machine learning, data sciences, and life sciences to report on cutting-edge and state-of-the-art computational algorithms in scientific computing and to identify computational and statistical challenges and open problems in machine learning and the life sciences. In addition, the workshop will provide a forum for an international and diverse group of researchers to foster communication, to facilitate new collaborative interactions, and to initiate joint research projects that will address the open and emerging issues and the computational and statistical challenges posed in machine learning and the life sciences. The three-day workshop will consist of presentations, posters, and group discussions that will stimulate an intensive exchange of ideas and foster fruitful interactions. This award supports the attendance of both researchers and graduate students, with priority given to graduate students, postdoctoral scholars, early career investigators, members of under-represented groups, and researchers who do not have other federal support. Scientific computing is an increasingly important tool in many areas of science and engineering, such as biomedical imaging, genomics, proteomics, phylogeny, computer vision, and precision medicine, allowing biological data and systems to be explored that are not amenable to theoretical or experimental investigations. Machine learning is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns, and make decisions with minimal human intervention. The advent of the big data era pushed machine learning to the forefront and has spurred broad interests in machine learning in recent years. The field of life sciences has advanced through a synergistic interplay between deep understanding of biology and mathematical techniques, especially from computational mathematics, probability, and statistics. Still, biologists are overwhelmed by the amount of data being generated and the new methods required for data-management. Quantitative theories are needed to help interpret and to contextualize observations. A variety of new challenges in scientific computing for machine learning have emerged in recent years that are related to the life sciences, such as developing predictive models for disorder detection, drug repurposing, toxicity prediction, electronic health record analysis, language translation, etc. These issues and many other open problems will be discussed among the diverse group of scientists participating in the workshop. More information is available at http://www.math.ttu.edu/scmlls2019/.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.