Abstract Recently, the use of machine learning in meteorology has increased greatly. While many machine learning methods are not new, university classes on machine learning are largely unavailable to meteorology students and are not required to become a meteorologist. The lack of formal instruction has contributed to perception that machine learning methods are “black boxes” and thus end-users are hesitant to apply the machine learning methods in their everyday workflow. To reduce the opaqueness of machine learning methods and lower hesitancy toward machine learning in meteorology, this paper provides a survey of some of the most common machine learning methods. A familiar meteorological example is used to contextualize the machine learning methods while also discussing machine learning topics using plain language. The following machine learning methods are demonstrated: linear regression, logistic regression, decision trees, random forest, gradient boosted decision trees, naïve Bayes, and support vector machines. Beyond discussing the different methods, the paper also contains discussions on the general machine learning process as well as best practices to enable readers to apply machine learning to their own datasets. Furthermore, all code (in the form of Jupyter notebooks and Google Colaboratory notebooks) used to make the examples in the paper is provided in an effort to catalyze the use of machine learning in meteorology.
more »
« less
Striosomes Mediate Value-Based Learning Vulnerable in Age and a Huntington's Disease Model.
In Brief: Friedman et al. find that specializedregions of the striatum, a key part of thebrain’s movement and motivation controlsystem, are essential for learning aboutthe values of good and bad outcomes ofdecisions. The learning signals instriosomes scale according to subjectivevalue and are vulnerable to decline withaging and in neurodegenerativedisorders.
more »
« less
- Award ID(s):
- 1810758
- PAR ID:
- 10228855
- Author(s) / Creator(s):
- ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more »
- Date Published:
- Journal Name:
- Cell
- ISSN:
- 1097-4172
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recognizing the value of engagement in learning, recent engineering education initiatives have worked to encourage all types of students to pursue engineering while also facilitating the construction of makerspaces on university campuses. Makerspaces have the potential to engage a broader range of students by providing unique and personalized pathways into engineering. While this aims to improve the quality of an engineer’s education, the reality settles in when we begin to question whether these makerspaces are, in fact, encouraging learning in engineering for all types of students. In this work, we focus on investigating how a university makerspace affords learning for female students. We implemented an in-depth phenomenologically based interviewing approach which involved a series of three 90-minute semi-structured interviews with six highly engaged female undergraduate students involved in different makerspaces at a single university. The purpose of these interviews was to engage the students in their experiences with the makerspaces and the projects that they work on in this space, so as to inform how these spaces afford learning, specifically the impact on female student learning. All interviews were conducted by the same female graduate student. This work focuses on the second interviews of two females who had student worker roles in their respective makerspaces on campus. All of the interviews for these two females were transcribed resulting in 180 pages of single-spaced transcriptions, and the second interviews were analyzed through two phases of qualitative data analysis. Types of learning emerged in multiple forms and are presented via case studies of each female participant. For case one, these types of learning include machines learning, social learning, design learning, and self-learning. In the second case, the types of learning are tool learning, resourceful learning, space learning, and management learning. These types of learning are then further discussed according to engineering education pedagogy and implications. Makerspaces are often labeled as “open, learning environments,” and this work demonstrates how these spaces facilitate unique forms of learning that engage these women in the makerspace.more » « less
-
Postulating that the act of making stimulates learning, a widespread effort prompted the integration of makerspaces on college campuses. From community colleges to research-based higher education institutions, large investments were and still are being made to advance the making spirit and encourage non-traditional learning in academic settings. While optimistic that students are taking advantage of the makerspace resources and are in fact learning from their experiences, there needs to be a more direct effort to understand the learning, if any, that is occurring in the makerspace. The makerspace is labeled as an open, learning environment where students are able to design, create, innovate, and collaborate [1, 2]. In response, we investigate the claims of this statement through the research question: how is learning experienced by female students in an academic makerspace? Female students in STEM, especially those engaged in makerspaces, have unique and uncharacteristic experiences that can lend way to various learning and pedagogical implications. The purpose of this paper is to highlight our methodological process for incorporating in-depth phenomenologically based interviewing and for utilizing open and axial coding methods to establish grounded theory. We interview five female students through purposeful maximum variation sampling and snowball sampling. Through a rigorous and iterative data analysis process of the ten-percent of the overall, we created a preliminary coding scheme that articulates how learning is occurring, what design skills are being learned, and what life skills are being learned. These preliminary findings show that not only are these female students learning by doing and learning how to problem solve in design, but they are also overcoming fears, developing patience, and communicating ideas in these design-oriented makerspaces.more » « less
-
Deep learning has gained substantial popularity in recent years. Developers mainly rely on libraries and tools to add deep learning capabilities to their software. What kinds of bugs are frequently found in such software? What are the root causes of such bugs? What impacts do such bugs have? Which stages of deep learning pipeline are more bug prone? Are there any antipatterns? Understanding such characteristics of bugs in deep learning software has the potential to foster the development of better deep learning platforms, debugging mechanisms, development practices, and encourage the development of analysis and verification frameworks. Therefore, we study 2716 high-quality posts from Stack Overflow and 500 bug fix commits from Github about five popular deep learning libraries Caffe, Keras, Tensorflow, Theano, and Torch to understand the types of bugs, root causes of bugs, impacts of bugs, bug-prone stage of deep learning pipeline as well as whether there are some common antipatterns found in this buggy software. The key findings of our study include: data bug and logic bug are the most severe bug types in deep learning software appearing more than 48% of the times, major root causes of these bugs are Incorrect Model Parameter (IPS) and Structural Inefficiency (SI) showing up more than 43% of the times.We have also found that the bugs in the usage of deep learning libraries have some common antipatterns.more » « less
-
Informal learning environments play a critical role in science, technology, engineering, and mathematics learning across the lifespan and are consequential in informing public understanding and engagement. This can be difficult to accomplish in life science where expertise thresholds and logistics involved with handling biological materials can restrict access. Community laboratories are informal learning environments that provide access to the resources necessary to carry out pursuits using enabling biotechnologies. We investigate a group of these spaces in order to ascertain how this occurs—with specific attention to how material and intellectual resources are structured and shape learning. Using surveys and focus group interviews, we explore a group of these spaces located in the United States. We found that the spaces examined offer learning activities that are sufficiently scaffolded and flexible as to promote personalized and community-driven practice. We discuss these findings in relation to informal learning environment design and learning.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1016/j.cell.2020.09.060
