More Like this

1. Bending the Trajectory of Field School Teaching and Learning through Active and Advocacy Archaeology

   https://doi.org/10.3390/humans3010002  

   Lambert, Shawn P.; Colaninno, Carol E. (March 2023, Humans)

   Many individuals practicing field-based research are subjected to sexual harassment and assault. This fact holds true for people engaged in archaeological field research and may be true for students who are just learning field methods while enrolled in an archaeological field school. We review some of our current research on the means of reducing and preventing sexual harassment and assault at archaeological field schools, as well as ways to create safer, more inclusive learning spaces. Additionally, we suggest that for the discipline to advance field school teaching and learning, we, as field directors, must situate ourselves as active and advocacy anthropologists: an approach that puts our students as a central focus when developing field-based pedagogy. As the authors of this work, we review our identities and positionality in conducting this research and in making meaning from the data we have collected. 

   more » « less
2. Similar: Submodular information measures based active learning in realistic scenarios

   Kothawade, Suraj; Beck, Nathan; Killamsetty, Krishnateja; Iyer, Rishabh (December 2021, Advances in neural information processing systems)

   Active learning has proven to be useful for minimizing labeling costs by selecting the most informative samples. However, existing active learning methods do not work well in realistic scenarios such as imbalance or rare classes, out-of-distribution data in the unlabeled set, and redundancy. In this work, we propose SIMILAR (Submodular Information Measures based actIve LeARning), a unified active learning framework using recently proposed submodular information measures (SIM) as acquisition functions. We argue that SIMILAR not only works in standard active learning, but also easily extends to the realistic settings considered above and acts as a one-stop solution for active learning that is scalable to large real-world datasets. Empirically, we show that SIMILAR significantly outperforms existing active learning algorithms by as much as ~5% - 18% in the case of rare classes and ~5% - 10% in the case of out-of-distribution data on several image classification tasks like CIFAR-10, MNIST, and ImageNet. SIMILAR is available as a part of the DISTIL toolkit: "this https URL". 

   more » « less
3. Uncertainty-aware molecular dynamics from Bayesian active learning for phase transformations and thermal transport in SiC

   https://doi.org/10.1038/s41524-023-00988-8  

   Xie, Yu; Vandermause, Jonathan; Ramakers, Senja; Protik, Nakib H.; Johansson, Anders; Kozinsky, Boris (March 2023, npj Computational Materials)

   Abstract Machine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomistic dynamics. Active learning methods have been recently developed to train force fields efficiently and automatically. Among them, Bayesian active learning utilizes principled uncertainty quantification to make data acquisition decisions. In this work, we present a general Bayesian active learning workflow, where the force field is constructed from a sparse Gaussian process regression model based on atomic cluster expansion descriptors. To circumvent the high computational cost of the sparse Gaussian process uncertainty calculation, we formulate a high-performance approximate mapping of the uncertainty and demonstrate a speedup of several orders of magnitude. We demonstrate the autonomous active learning workflow by training a Bayesian force field model for silicon carbide (SiC) polymorphs in only a few days of computer time and show that pressure-induced phase transformations are accurately captured. The resulting model exhibits close agreement with both ab initio calculations and experimental measurements, and outperforms existing empirical models on vibrational and thermal properties. The active learning workflow readily generalizes to a wide range of material systems and accelerates their computational understanding. 

   more » « less
4. GALAXY: Graph-based Active Learning at the Extreme

   Zhang, Jifan; Katz-Samuels, Julian; Nowak, Robert (January 2022, International Conference on Machine Learning)

   Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a small fraction of the overall dataset -- most of the data may be viewed as an out-of-distribution or irrelevant class. This leads to extreme class-imbalance, and our theory and methods focus on this core issue. We propose a new strategy for active learning called GALAXY (Graph-based Active Learning At the eXtrEme), which blends ideas from graph-based active learning and deep learning. GALAXY automatically and adaptively selects more class-balanced examples for labeling than most other methods for active learning. Our theory shows that GALAXY performs a refined form of uncertainty sampling that gathers a much more class-balanced dataset than vanilla uncertainty sampling. Experimentally, we demonstrate GALAXY's superiority over existing state-of-art deep active learning algorithms in unbalanced vision classification settings generated from popular datasets. 

   more » « less
5. Teaching Ethnographic Methods for Cultural Anthropology: Current Practices and Needed Innovation

   https://doi.org/10.22582/ta.v11i2.634  

   Ruth, Alissa; Woolard, Katherine; Sangaramoorthy, Thurka; McKinley Jones Brayboy, Bryan; Beresford, Melissa; Brewis, Alexandra; Bernard, H. Russell; Glegziabher, Meskerem Z.; Hardin, Jessic; Harper, Krista; et al (March 2022, Teaching Anthropology)

   Historically, ethnographic methods were learned by cultural anthropology students in individual research projects. This approach creates challenges for teaching in ways that respond to the next generation’s calls to decenter anthropology’s White, heteropatriarchal voices and engage in collaborative community-based research. Analyzing syllabi from 107 ethnographic methods training courses from the United States, we find the tradition of the “lone researcher” persists and is the basis of ethnographic training for the next generation. There is little evidence of either active reflection or team-based pedagogy, both identified as necessary to meet career opportunities and diversification goals for the wider field of cultural anthropology. However, we also find that, by centering the completion of largely individual research projects, most ethnographic methods courses otherwise adhere to best practices in regard to experiential and active learning. Based on the analysis of syllabi in combination with current pedagogical literature, we suggest how cultural anthropologists can revise their ethnographic methods courses to incorporate pedagogy that promotes methodologies and skills to align with the needs of today’s students and communities. 

   more » « less