In the last installment of the Dataflow course series, we will introduce the components of the Dataflow operational model. We will examine tools and techniques for troubleshooting and optimizing pipeline performance. We will then review testing, deployment, and reliability best practices for Dataflow pipelines. We will conclude with a review of Templates, which makes it easy to scale Dataflow pipelines to organizations with hundreds of users. These lessons will help ensure that your data platform is stable and resilient to unanticipated circumstances.

In the third course of Machine Learning Engineering for Production Specialization, you will build models for different serving environments; implement tools and techniques to effectively manage your modeling resources and best serve offline and online inference requests; and use analytics tools and performance metrics to address model fairness, explainability issues, and mitigate bottlenecks. Understanding machine learning and deep learning concepts is essential, but if you’re looking to build an effective AI career, you need production engineering capabilities as well. Machine learning engineering for production combines the foundational concepts of machine learning with the functional expertise of modern software development and engineering roles to help you develop production-ready skills. Week 1: Neural Architecture Search Week 2: Model Resource Management Techniques Week 3: High-Performance Modeling Week 4: Model Analysis Week 5: Interpretability

Useful quantitative models help you to make informed decisions both in situations in which the factors affecting your decision are clear, as well as in situations in which some important factors are not clear at all. In this course, you can learn how to create quantitative models to reflect complex realities, and how to include in your model elements of risk and uncertainty. You’ll also learn the methods for creating predictive models for identifying optimal choices; and how those choices change in response to changes in the model’s assumptions. You’ll also learn the basics of the measurement and management of risk. By the end of this course, you’ll be able to build your own models with your own data, so that you can begin making data-informed decisions. You’ll also be prepared for the next course in the Specialization.

By the end of this third course in the Total Data Quality Specialization, learners will be able to: 1. Learn about design tools and techniques for maximizing TDQ across all stages of the TDQ framework during a data collection or a data gathering process. 2. Identify aspects of the data generating or data gathering process that impact TDQ and be able to assess whether and how such aspects can be measured. 3. Understand TDQ maximization strategies that can be applied when gathering designed and found/organic data. 4. Develop solutions to hypothetical design problems arising during the process of data collection or data gathering and processing. This specialization as a whole aims to explore the Total Data Quality framework in depth and provide learners with more information about the detailed evaluation of total data quality that needs to happen prior to data analysis. The goal is for learners to incorporate evaluations of data quality into their process as a critical component for all projects. We sincerely hope to disseminate knowledge about total data quality to all learners, such as data scientists and quantitative analysts, who have not had sufficient training in the initial steps of the data science process that focus on data collection and evaluation of data quality. We feel that extensive knowledge of data science techniques and statistical analysis procedures will not help a quantitative research study if the data collected/gathered are not of sufficiently high quality. This specialization will focus on the essential first steps in any type of scientific investigation using data: either generating or gathering data, understanding where the data come from, evaluating the quality of the data, and taking steps to maximize the quality of the data prior to performing any kind of statistical analysis or applying data science techniques to answer research questions. Given this focus, there will be little material on the analysis of data, which is covered in myriad existing Coursera specializations. The primary focus of this specialization will be on understanding and maximizing data quality prior to analysis.

Have you ever had the perfect data science experience? The data pull went perfectly. There were no merging errors or missing data. Hypotheses were clearly defined prior to analyses. Randomization was performed for the treatment of interest. The analytic plan was outlined prior to analysis and followed exactly. The conclusions were clear and actionable decisions were obvious. Has that every happened to you? Of course not. Data analysis in real life is messy. How does one manage a team facing real data analyses? In this one-week course, we contrast the ideal with what happens in real life. By contrasting the ideal, you will learn key concepts that will help you manage real life analyses. This is a focused course designed to rapidly get you up to speed on doing data science in real life. Our goal was to make this as convenient as possible for you without sacrificing any essential content. We've left the technical information aside so that you can focus on managing your team and moving it forward. After completing this course you will know how to: 1, Describe the “perfect” data science experience 2. Identify strengths and weaknesses in experimental designs 3. Describe possible pitfalls when pulling / assembling data and learn solutions for managing data pulls. 4. Challenge statistical modeling assumptions and drive feedback to data analysts 5. Describe common pitfalls in communicating data analyses 6. Get a glimpse into a day in the life of a data analysis manager. The course will be taught at a conceptual level for active managers of data scientists and statisticians. Some key concepts being discussed include: 1. Experimental design, randomization, A/B testing 2. Causal inference, counterfactuals, 3. Strategies for managing data quality. 4. Bias and confounding 5. Contrasting machine learning versus classical statistical inference Course promo: https://www.youtube.com/watch?v=9BIYmw5wnBI Course cover image by Jonathan Gross. Creative Commons BY-ND https://flic.kr/p/q1vudb

Network analysis is a long-standing methodology used to understand the relationships between words and actors in the broader networks in which they exist. This course covers network analysis as it pertains to marketing data, specifically text datasets and social networks. Learners walk through a conceptual overview of network analysis and dive into real-world datasets through instructor-led tutorials in Python. The course concludes with a major project. This course can be taken for academic credit as part of CU Boulder’s Master of Science in Data Science (MS-DS) degree offered on the Coursera platform. The MS-DS is an interdisciplinary degree that brings together faculty from CU Boulder’s departments of Applied Mathematics, Computer Science, Information Science, and others. With performance-based admissions and no application process, the MS-DS is ideal for individuals with a broad range of undergraduate education and/or professional experience in computer science, information science, mathematics, and statistics. Learn more about the MS-DS program at https://www.coursera.org/degrees/master-of-science-data-science-boulder.

In this 1-hour long project-based course, you will learn how to optimize a two-asset portfolio at the optimum risk-to-return with finding the maximum Sharpe ratio. To achieve this, we will be working around the Sharpe ratios of two given assets, we will find the efficient frontier of these assets, and find where they intersect the best by utilizing the Markowitz Model. The content of this course draws on the knowledge of Project: Compare Stock Returns with Google Sheets, so you are highly recommended to take it first if you are not familiar with how the Sharpe ratio is calculated and don’t have an understanding of how the risk-to-return metrics work. Note: This course works best for learners who are based in the North America region. We're currently working on providing the same experience in other regions. This course's content is not intended to be investment advice and does not constitute an offer to perform any operations in the regulated or unregulated financial market.

In every domain it is critical to decision making to understand whether differences exist between two or more groups of things or outcomes. In this course you will test for differences with the One-Way ANOVA analysis of variance technique. You will also learn how to design the test and apply tactics so that you are able to confidently report statistical significance between and within groups if it exists. For this course, we will work side-by-side in the free-to-use software Google Sheets. By the end of this course, you will be able to apply ANOVA and post hoc tests using any spreadsheet software and you will be able to confidently report levels of statistical significance in groups. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

This is a self-paced lab that takes place in the Google Cloud console. In this lab you will set up Monitoring and visualizing metrics from a Kubernetes Engine cluster

In the fourth course of the Deep Learning Specialization, you will understand how computer vision has evolved and become familiar with its exciting applications such as autonomous driving, face recognition, reading radiology images, and more. By the end, you will be able to build a convolutional neural network, including recent variations such as residual networks; apply convolutional networks to visual detection and recognition tasks; and use neural style transfer to generate art and apply these algorithms to a variety of image, video, and other 2D or 3D data. The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI.