Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
34,560
result(s) for
"Active-learning"
Sort by:
Active learning for data streams: a survey
Online active learning is a paradigm in machine learning that aims to select the most informative data points to label from a data stream. The problem of minimizing the cost associated with collecting labeled observations has gained a lot of attention in recent years, particularly in real-world applications where data is only available in an unlabeled form. Annotating each observation can be time-consuming and costly, making it difficult to obtain large amounts of labeled data. To overcome this issue, many active learning strategies have been proposed in the last decades, aiming to select the most informative observations for labeling in order to improve the performance of machine learning models. These approaches can be broadly divided into two categories: static pool-based and stream-based active learning. Pool-based active learning involves selecting a subset of observations from a closed pool of unlabeled data, and it has been the focus of many surveys and literature reviews. However, the growing availability of data streams has led to an increase in the number of approaches that focus on online active learning, which involves continuously selecting and labeling observations as they arrive in a stream. This work aims to provide an overview of the most recently proposed approaches for selecting the most informative observations from data streams in real time. We review the various techniques that have been proposed and discuss their strengths and limitations, as well as the challenges and opportunities that exist in this area of research.
Journal Article
Foxfire approach : inspiration for classrooms and beyond
\"This collection of essays by Foxfire practitioners represents the wide range of adaptations by educators of the pedagogical orientation of the Foxfire Magazine and Foxfire Programs for Teachers\"--Back cover.
Book
Active Learning Query Strategies for Classification, Regression, and Clustering: A Survey
Generally, data is available abundantly in unlabeled form, and its annotation requires some cost. The labeling, as well as learning cost, can be minimized by learning with the minimum labeled data instances. Active learning (AL), learns from a few labeled data instances with the additional facility of querying the labels of instances from an expert annotator or oracle. The active learner uses an instance selection strategy for selecting those critical query instances, which reduce the generalization error as fast as possible. This process results in a refined training dataset, which helps in minimizing the overall cost. The key to the success of AL is query strategies that select the candidate query instances and help the learner in learning a valid hypothesis. This survey reviews AL query strategies for classification, regression, and clustering under the pool-based AL scenario. The query strategies under classification are further divided into: informative-based, representative-based, informative- and representative-based, and others. Also, more advanced query strategies based on reinforcement learning and deep learning, along with query strategies under the realistic environment setting, are presented. After a rigorous mathematical analysis of AL strategies, this work presents a comparative analysis of these strategies. Finally, implementation guide, applications, and challenges of AL are discussed.
Journal Article
Learning as a generative activity : eight learning strategies that promote understanding
This book presents eight evidence-based strategies that promote generative learning, which enables learners to apply their knowledge to new problems.
Book
Effect of active learning versus traditional lecturing on the learning achievement of college students in humanities and social sciences: a meta-analysis
A previous meta-analysis found that active learning has a positive impact on learning achievements for college students in STEM fields of study. However, no similar meta-analyses have been conducted in the humanities and social sciences. Because major dissimilarities may exist between different fields or domain of knowledge, there can be issues with transferring research findings or knowledge across fields. We therefore meta-analyzed 104 studies that used assessment scores to compare the learning achieved by college students in humanities and social science programs under active instruction versus traditional lecturing. Student performance on assessment scores was found to be higher by 0.489 standard deviations under active instruction (Z = 6.521, p < 0.001, k = 111, N = 15,896). The relative beneficial effect of active instruction was found to be higher for some course subject matters (i.e., Sociology, Psychology, Language, Education, and Economics), for smaller (≤ 20 students) rather than larger class or group sizes, and for upper level rather than introductory courses. Analyses further suggest that these findings are not affected by publication bias.
Journal Article
Actions of their own to learn : studies in knowing, acting, and being
\"What does it mean to take actions of one's own to learn? How do human beings create meaning for themselves and with others? How can learners' active efforts to build knowledge be encouraged and supported? In this edited compilation, scholars from a diverse range of academic and professional backgrounds address these questions, grounded in the conviction that the ability to take effective action of one's own to learn is itself an essential form. In an era of dramatic social, environmental and political change, the need to access vast amounts of information to make decisions demands that learners become active agents in their own knowledge development. Educators are transforming ideas about their role(s) as they strive to provide guidance to help learners take the lead in their own learning. Learners are building new ideas about their capacities to gather and organize information while working with others. No longer simply consumers of information, they are beginning to see themselves as capable and effective researchers. Researchers are also expanding ideas about their knowledge-gathering work and identities. No longer simply reporters of information, researchers are seeing themselves as learners, as they engage in deeper, more collaborative ways with participants in their research. Chapter authors describe their dedicated, and often career long journeys to show the vital connections between knowledge, acting to learn, identity and being. To engage in this work means disrupting traditional ideas about how knowledge is most effectively acquired. This book will inspire researchers, educators and educational planners as they build the kinds of new participative structures needed to support individual and collective actions to learn\"-- Provided by publisher.
Book
Scaling deep learning for materials discovery
Novel functional materials enable fundamental breakthroughs across technological applications from clean energy to information processing
1
–
11
. From microchips to batteries and photovoltaics, discovery of inorganic crystals has been bottlenecked by expensive trial-and-error approaches. Concurrently, deep-learning models for language, vision and biology have showcased emergent predictive capabilities with increasing data and computation
12
–
14
. Here we show that graph networks trained at scale can reach unprecedented levels of generalization, improving the efficiency of materials discovery by an order of magnitude. Building on 48,000 stable crystals identified in continuing studies
15
–
17
, improved efficiency enables the discovery of 2.2 million structures below the current convex hull, many of which escaped previous human chemical intuition. Our work represents an order-of-magnitude expansion in stable materials known to humanity. Stable discoveries that are on the final convex hull will be made available to screen for technological applications, as we demonstrate for layered materials and solid-electrolyte candidates. Of the stable structures, 736 have already been independently experimentally realized. The scale and diversity of hundreds of millions of first-principles calculations also unlock modelling capabilities for downstream applications, leading in particular to highly accurate and robust learned interatomic potentials that can be used in condensed-phase molecular-dynamics simulations and high-fidelity zero-shot prediction of ionic conductivity.
A protocol using large-scale training of graph networks enables high-throughput discovery of novel stable structures and led to the identification of 2.2 million crystal structures, of which 381,000 are newly discovered stable materials.
Journal Article
An autonomous laboratory for the accelerated synthesis of novel materials
To close the gap between the rates of computational screening and experimental realization of novel materials
, we introduce the A-Lab, an autonomous laboratory for the solid-state synthesis of inorganic powders. This platform uses computations, historical data from the literature, machine learning (ML) and active learning to plan and interpret the outcomes of experiments performed using robotics. Over 17 days of continuous operation, the A-Lab realized 41 novel compounds from a set of 58 targets including a variety of oxides and phosphates that were identified using large-scale ab initio phase-stability data from the Materials Project and Google DeepMind. Synthesis recipes were proposed by natural-language models trained on the literature and optimized using an active-learning approach grounded in thermodynamics. Analysis of the failed syntheses provides direct and actionable suggestions to improve current techniques for materials screening and synthesis design. The high success rate demonstrates the effectiveness of artificial-intelligence-driven platforms for autonomous materials discovery and motivates further integration of computations, historical knowledge and robotics.
Journal Article