97,489 research outputs found
Joshua Davis: Author of Spare Parts
No full textCitation: K-State First (2016). Joshua Davis: Author of Spare Parts [Flier]. Manhattan, Kansas: K-State First.Flyer advertising Joshua Davis's author talk at Kansas State University
Steven Johnson Author Talk Poster
No full textK-State Book NetworkA poster advertising an author talk by Steven Johnson at Kansas State University on September 3, 2014. Steven Johnson's book "The Ghost Map" was the 2014-2015 common book
Guided Zoom: Zooming into Network Evidence to Refine Fine-Grained Model Decisions
No full textIn state-of-the-art deep single-label classification models, the top-k (k = 2,3,4,....) accuracy is usually significantly higher than the top-1 accuracy. This is more evident in fine-grained datasets, where differences between classes are quite subtle. Exploiting the information provided in the top k predicted classes boosts the final prediction of a model. We propose Guided Zoom, a novel way in which explainabitity could be used to improve model performance. We do so by making sure the model has "the right reasons" fora prediction. The reason/evidence upon which a deep neural network makes a prediction is defined to be the grounding, in the pixel space, for a specific class conditional probability in the model output. Guided Zoom examines how reasonable the evidence used to make each of the top-k predictions is. Test time evidence is deemed reasonable if it is coherent with evidence used to make similar correct decisions at training time. This leads to better informed predictions. We explore a variety of grounding techniques and study their complementarity for computing evidence. We show that Guided Zoom results in an improvement of a model's classification accuracy and achieves state-of-the-art classification performance on four fine-grained classification datasets
Guided Zoom: Zooming into Network Evidence to Refine Fine-Grained Model Decisions
No full textIn state-of-the-art deep single-label classification models, the top-kk (k=2,3,4, \dots)(k=2,3,4,⋯) accuracy is usually significantly higher than the top-1 accuracy. This is more evident in fine-grained datasets, where differences between classes are quite subtle. Exploiting the information provided in the top kk predicted classes boosts the final prediction of a model. We propose Guided Zoom, a novel way in which explainability could be used to improve model performance. We do so by making sure the model has 'the right reasons' for a prediction. The reason/evidence upon which a deep neural network makes a prediction is defined to be the grounding, in the pixel space, for a specific class conditional probability in the model output. Guided Zoom examines how reasonable the evidence used to make each of the top-kk predictions is. Test time evidence is deemed reasonable if it is coherent with evidence used to make similar correct decisions at training time. This leads to better informed predictions. We explore a variety of grounding techniques and study their complementarity for computing evidence. We show that Guided Zoom results in an improvement of a model's classification accuracy and achieves state-of-the-art classification performance on four fine-grained classification datasets. Our code is available at https://github.com/andreazuna89/Guided-Zoom
Guided Zoom: Questioning Network Evidence for Fine-Grained Classification
No full textWe propose Guided Zoom, an approach that utilizes spatial grounding of a model’s decision to make more informed predictions. It does so by making sure the model has “the right reasons” for a prediction, defined as reasons that are coherent with those used to make similar correct decisions at training time. The reason/evidence upon which a deep convolutional neural network makes a prediction is defined to be the spatial grounding, in the pixel space, for a specific class conditional probability in the model output. Guided Zoom examines how reasonable such evidence is for each of the top-k predicted classes, rather than solely trusting the top-1 prediction. We show that Guided Zoom improves the classification accuracy of a deep convolutional neural network model and obtains state-of-the-art results on three fine-grained classification benchmark datasets
Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
No full textNeuro-Symbolic (NeSy) predictive models hold the promise of improved compliance with given constraints, systematic generalization, and interpretability, as they
allow to infer labels that are consistent with some prior knowledge by reasoning
over high-level concepts extracted from sub-symbolic inputs. It was recently shown
that NeSy predictors are affected by reasoning shortcuts: they can attain high accuracy but by leveraging concepts with unintended semantics, thus coming short of
their promised advantages. Yet, a systematic characterization of reasoning shortcuts
and of potential mitigation strategies is missing. This work fills this gap by characterizing them as unintended optima of the learning objective and identifying four
key conditions behind their occurrence. Based on this, we derive several natural
mitigation strategies, and analyze their efficacy both theoretically and empirically.
Our analysis shows reasoning shortcuts are difficult to deal with, casting doubts on
the trustworthiness and interpretability of existing NeSy solutions
Going Beyond Counting First Authors in Author Co-citation Analysis
No full textThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Appropriate Similarity Measures for Author Cocitation Analysis
No full textWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Expanding “Communities and Collections” in the K-State Research Exchange (K-REx) to benefit the K-State Community and Beyond
No full textKansas State University has used its institutional repository, the K-State Research Exchange (K-REx), to store and share its first year experience program, K-State First, and notably its common reading program, K-State First Book. We have done so with the aim that the accessibility and preservation of these documents ensures program stability, promotes engagement with first year programming, and provides the ability to foster growth,educational opportunities, and community building outside of K-State. Moving away from research concentrated repositories and taking a more holistic approach to scholarship, especially when realizing the pedagogical significance of collaborative campus programming, institutions can showcase, discover, preserve, and grow programs that shape campus communities and engagement.
This session will provide an overview of K-REx and spotlight the digital archive of the university’s first year experience program and common reading program, K-State First Book. We will discuss the benefits and challenges to expanding the purview of your repositories. We talkthrough the types of materials we decide to host in our repository and why we share what we do. We will also provide recommendations on new ways to evaluate what belongs in institutional repositories and how this diversity can benefit your program, your institution, the community, and others
Ready Player One Program Event Poster
No full textK-State Book NetworkA poster advertising an author talk by Ernest Cline at Kansas State University on October 10, 2013. Ernest Cline's book "Ready Player One" was selected as the 2013-2014 common book
- …
