Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
239,042
result(s) for
"Curriculum learning"
Sort by:
Development of a Course on Complex Humanitarian Emergencies: Preparation for the Impact of Climate Change
Purpose The effects of climate change are far‐reaching and multifactorial, with potential impacts on food security and conflict. Large population movements, whether from the aftermath of natural disasters or resulting from conflict, can precipitate the need for humanitarian response in what can become complex humanitarian emergencies (CHEs). Nurses need to be prepared to respond to affected communities in need, whether the emergency is domestic or global. The purpose of the article is to describe a novel course for nursing students interested in practice within the confines of CHEs and natural disasters. Methods and Framework The authors used the Sphere Humanitarian Charter and Minimum Standards as a practical framework to inform the course development. They completed a review of the literature on the interaction on climate change, conflict and health, and competencies related to working CHEs. Resettled refugees, as well as experts in the area of humanitarian response, recovery, and mitigation from the Centers for Disease Control and Prevention and nongovernmental organizations further informed the development of the course. Clinical Relevance This course prepares the nursing workforce to respond appropriately to large population movements that may arise from the aftermath of natural disasters or conflict, both of which can comprise a complex humanitarian disaster. Using The Sphere Project e‐learning course, students learn about the Sphere Project, which works to ensure accountability and quality in humanitarian response and offers core minimal standards for technical assistance. These guidelines are seen globally as the gold standard for humanitarian response and address many of the competencies for disaster nursing (http://www.sphereproject.org/learning/e-learning-course/).
Journal Article
Curriculum Learning: A Survey
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs. Curriculum learning strategies have been successfully employed in all areas of machine learning, in a wide range of tasks. However, the necessity of finding a way to rank the samples from easy to hard, as well as the right pacing function for introducing more difficult data can limit the usage of the curriculum approaches. In this survey, we show how these limits have been tackled in the literature, and we present different curriculum learning instantiations for various tasks in machine learning. We construct a multi-perspective taxonomy of curriculum learning approaches by hand, considering various classification criteria. We further build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm, linking the discovered clusters with our taxonomy. At the end, we provide some interesting directions for future work.
Journal Article
Future wise : educating our children for a changing world
\"How to teach big understandings and the ideas that matter most. Everyone has an opinion about education, and teachers face pressures from Common Core content standards, high-stakes testing, and countless other directions. But how do we know what today's learners will really need to know in the future? Future Wise: Educating Our Children for a Changing World is a toolkit for approaching that question with new insight. There is no one answer to the question of what's worth teaching, but with the tools in this book, you'll be one step closer to constructing a curriculum that prepares students for whatever situations they might face in the future. K-12 teachers and administrators play a crucial role in building a thriving society. David Perkins, founding member and co-director of Project Zero at Harvard's Graduate School of Education, argues that curriculum is one of the most important elements of making students ready for the world of tomorrow. In Future Wise, you'll learn concepts, curriculum criteria, and techniques for prioritizing content so you can guide students toward the big understandings that matter. Understand how learners use knowledge in life after graduation Learn strategies for teaching critical thinking and addressing big questions Identify top priorities when it comes to disciplines and content areas Gain curriculum design skills that make the most of learning across the years of education Future Wise presents a brand new framework for thinking about education. Curriculum can be one of the hardest things for teachers and administrators to change, but David Perkins shows that only by reimagining what we teach can we lead students down the road to functional knowledge. Future Wise is the practical guidebook you need to embark on this important quest\"-- Provided by publisher.
Book
Human-in-the-loop machine learning: a state of the art
Researchers are defining new types of interactions between humans and machine learning algorithms generically called human-in-the-loop machine learning. Depending on who is in control of the learning process, we can identify: active learning, in which the system remains in control; interactive machine learning, in which there is a closer interaction between users and learning systems; and machine teaching, where human domain experts have control over the learning process. Aside from control, humans can also be involved in the learning process in other ways. In curriculum learning human domain experts try to impose some structure on the examples presented to improve the learning; in explainable AI the focus is on the ability of the model to explain to humans why a given solution was chosen. This collaboration between AI models and humans should not be limited only to the learning process; if we go further, we can see other terms that arise such as Usable and Useful AI. In this paper we review the state of the art of the techniques involved in the new forms of relationship between humans and ML algorithms. Our contribution is not merely listing the different approaches, but to provide definitions clarifying confusing, varied and sometimes contradictory terms; to elucidate and determine the boundaries between the different methods; and to correlate all the techniques searching for the connections and influences between them.
Journal Article
Extending the Capabilities of Reinforcement Learning Through Curriculum: A Review of Methods and Applications
Reinforcement learning has long been advertised as the one with the capability to intelligently mimic and understand human learning and behavior. While the upshot of the field’s advances is not underrated, its applicability and extension to large, complex and highly dynamic environments remain inefficient, inaccurate or unsolved. Curriculum learning presents an intuitive yet elegant solution to these problems and when incorporated into the solution, provides a structured approach to alleviate some of the core challenges. As reinforcement learning framework proceeds to tackle harder challenges, it necessitates the study of essential support frameworks including curriculum learning. Through this paper, we review the current state-of-the-art in the field of curriculum-based reinforcement learning. We analyze and classify numerous scientific articles and present a summary of their methodologies and applications. In addition to the detailed review and analysis of the targeted algorithms, we summarise the current progress in the field by tabulating distinct identifying features of reviewed works with respect to their curriculum design methodology and applications.
Journal Article
From MNIST to ImageNet and back: benchmarking continual curriculum learning
Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop models and learning strategies that present high robustness in dynamic environments. This goal is realized by designing strategies that simultaneously foster the incorporation of new knowledge while avoiding forgetting past knowledge. The landscape of CL research is fragmented into several learning evaluation protocols, comprising different learning tasks, datasets, and evaluation metrics. Additionally, the benchmarks adopted so far are still distant from the complexity of real-world scenarios, and are usually tailored to highlight capabilities specific to certain strategies. In such a landscape, it is hard to clearly and objectively assess models and strategies. In this work, we fill this gap for CL on image data by introducing two novel CL benchmarks that involve multiple heterogeneous tasks from six image datasets, with varying levels of complexity and quality. Our aim is to fairly evaluate current state-of-the-art CL strategies on a common ground that is closer to complex real-world scenarios. We additionally structure our benchmarks so that tasks are presented in increasing and decreasing order of complexity—according to a curriculum—in order to evaluate if current CL models are able to exploit structure across tasks. We devote particular emphasis to providing the CL community with a rigorous and reproducible evaluation protocol for measuring the ability of a model to generalize and not to forget while learning. Furthermore, we provide an extensive experimental evaluation showing that popular CL strategies, when challenged with our proposed benchmarks, yield sub-par performance, high levels of forgetting, and present a limited ability to effectively leverage curriculum task ordering. We believe that these results highlight the need for rigorous comparisons in future CL works as well as pave the way to design new CL strategies that are able to deal with more complex scenarios.
Journal Article