30,842 research outputs found
Recommended from our members
French operatic spectacle in the twentieth century
No full textThis is a 12 chapter multi-author book co-edited by myself and Caroline Potter of the University of Kingston. My authorship consists of a chapter and Preface and Acknowledgements (co-authored). My Chapter (5) is entitled 'French operatic spectacle in the twentieth-century' and runs from pp. 117–159
slickml/slick-ml: Version 0.2.1
No full textWhat's Changed
Fixed
Bumped version and updated CHANGELOG by @amirhessam88 in https://github.com/slickml/slick-ml/pull/178
Fixed badges in API docs by @amirhessam88 in https://github.com/slickml/slick-ml/pull/174
Added
Rolled out basic CLI functionalities by @amirhessam88 in https://github.com/slickml/slick-ml/pull/177, https://github.com/slickml/slick-ml/pull/176
Rolled out unit-tests to cover save-path parameter in all visualization modules by @amirhessam88 in https://github.com/slickml/slick-ml/pull/175
Enabled threshold in .coveragerc and codecov.yml to protect test coverages by @amirhessam88 in https://github.com/slickml/slick-ml/pull/173
♀️ Notes
More examples using ZenML, BentoML and Prefect coming soon .
Full Changelog https://github.com/slickml/slick-ml/compare/v0.2.0...v0.2.
slickml/slick-ml: Version 0.2.0
No full textWhat's Changed
Fixed
XGBoostHyperOptimizer refactor by @amirhessam88 in https://github.com/slickml/slick-ml/pull/169
Added
Rolled out type checking with mypy by @amirhessam88 in https://github.com/slickml/slick-ml/pull/171
Rolled out more flake8 plugins by @amirhessam88 in https://github.com/slickml/slick-ml/pull/170
♀️ Notes
More examples using ZenML, BentoML and Prefect coming soon .
Full Changelog https://github.com/slickml/slick-ml/compare/v0.2.0-beta.2...v0.2.
slickml/slick-ml: Version 0.2.0-beta.2
No full textWhat's Changed
Fixed
XGBoostBayesianOptimizer refactor by @amirhessam88 in https://github.com/slickml/slick-ml/pull/164
XGBoostFeatureSelector refactor by @amirhessam88 in https://github.com/slickml/slick-ml/pull/156
XGBoostFeatureSelector callbacks by @amirhessam88 in https://github.com/slickml/slick-ml/pull/161
tox.ini and package dependencies including poetry-core v1.3.2 by @amirhessam88 in https://github.com/slickml/slick-ml/pull/151,https://github.com/slickml/slick-ml/pull/160
codecov-action v3 by @amirhessam88 in https://github.com/slickml/slick-ml/pull/157
Default reviewers and new members by @amirhessam88 in https://github.com/slickml/slick-ml/pull/155
Added
conftest.py for pytest unit-tests by @amirhessam88 in https://github.com/slickml/slick-ml/pull/158
ascii art banner ideas to assets/designs and poe greet by @amirhessam88 in https://github.com/slickml/slick-ml/pull/153, https://github.com/slickml/slick-ml/pull/159
BaseXGBoostEstimator by @amirhessam88 in https://github.com/slickml/slick-ml/pull/162
♀️ Notes
The refactored XGBoostHyperOpt class for optimization will be released in version 0.2.0-rc soon .
Full Changelog https://github.com/slickml/slick-ml/compare/v0.2.0-beta.1...v0.2.0-beta.
Metadata Representations for Queryable ML Model Zoos
No full textMachine learning (ML) practitioners and organizations are building model zoos of pre-trained models, containing metadata describing properties of the ML models and datasets that are useful for reporting, auditing, reproducibility, and interpretability purposes. The metatada is currently not standardised; its expressivity is limited; and there is no interoperable way to store and query it. Consequently, model search, reuse, comparison, and composition are hindered. In this paper, we advocate for standardized ML model metadata representation and management, proposing a toolkit supported to help practitioners manage and query that metadata.Web Information SystemsHuman-Centred Artificial Intelligenc
A Manifesto of Nodalism
Get PDFThis paper proposes the notion of Nodalism as a means describing contemporary culture and of understanding my own creative practice in electronic music composition. It draws on theories and ideas from Kirby, Bauman, Bourriaud, Deleuze, Guatarri, and Gochenour, to demonstrate how networks of ideas or connectionist neural models of cognitive behaviour can be used to contextualize, understand and become a creative tool for the creation of contemporary electronic music
ACL2(ml):machine-learning for ACL2
Get PDFACL2(ml) is an extension for the Emacs interface of ACL2. This tool uses machine-learning to help the ACL2 user during the proof-development. Namely, ACL2(ml) gives hints to the user in the form of families of similar theorems, and generates auxiliary lemmas automatically. In this paper, we present the two most recent extensions for ACL2(ml). First, ACL2(ml) can suggest now families of similar function definitions, in addition to the families of similar theorems. Second, the lemma generation tool implemented in ACL2(ml) has been improved with a method to generate preconditions using the guard mechanism of ACL2. The user of ACL2(ml) can also invoke directly the latter extension to obtain preconditions for his own conjectures.</p
Optimizing ML Inference Queries Under Constraints
No full textThe proliferation of pre-trained ML models in public Web-based model zoos facilitates the engineering of ML pipelines to address complex inference queries over datasets and streams of unstructured content. Constructing optimal plan for a query is hard, especially when constraints (e.g. accuracy or execution time) must be taken into consideration, and the complexity of the inference query increases. To address this issue, we propose a method for optimizing ML inference queries that selects the most suitable ML models to use, as well as the order in which those models are executed. We formally define the constraint-based ML inference query optimization problem, formulate it as a Mixed Integer Programming (MIP) problem, and develop an optimizer that maximizes accuracy given constraints. This optimizer is capable of navigating a large search space to identify optimal query plans on various model zoos.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Web Information SystemsHuman-Centred Artificial Intelligenc
Lon Smith, a volunteer from Ann Arbor Ml
No full text"PAR [Patricia A. Renick] on platform making best guesses on placement of the copter. Lon Smith, a volunteer from Ann Arbor Ml stays in town for several months helping PAR. Lon volunteered after he hear PAR give a lecture on her work in Michigan.The forthcoming Triceracopter project was part of her lecture." -- Laura H. Chapma
Analysis of natural products from Neurolama lobata as candidate antifilarial agents against the parasitic nematode Brugia pahangi
No full textLymphatic filariasis (LF) is a neglected tropical disease currently afflicting over 125 million people in 73 countries (GAELF). Among others, a major issue barring the success of the World Health Organization\u27s efforts to eradicate LF is emerging genetic resistance of the parasites to antifilarial medications. These issues may be alleviated through the development of novel antifilarial drugs from bioactive secondary metabolites from plants (Murthy, Joseph, and Murthy 2011). Two sesquiterpene lactones, Neurolenin A and Neurolenin B, from the Central American shrub weed Neurolaena lobata, are tested for bioactivity against the filarial nematode Brugia pahangi. Tests for in vitro mortality of Neurolenin A, Neurolenin B, and 1:1 Neurolenin A+B against adult male, adult female, and larval stage 3 (L3) B.pahangi are performed (doses: 0.6 μg/mL, 0.5 μg/mL, and 0.4 μg/mL). RNA-seq is also performed on mRNA from adult female B. pahangi treated either with crude ethanolic N. lobata extract (300 μg/mL) (n=45), Neurolenin B (0.5 μg/mL) (n=45), or nothing (negative control) (n=45) to begin elucidating the role of differential gene expression in the mechanism of action for N. lobata and Neurolenin B. A bioinformatics workflow is also developed for analysis of RNA-seq data. Neurolenin A is not significantly bioactive against all tested B. pahangi in an in vitro toxicity test of 80 hours. However, Neurolenin B and 1:1 Neurolenin mix are bioactive against B. pahangi. Neurolenin B and 1:1 Neurolenin A+B are shown to interrupt the L3-to-L4 molt. RNAseq confirms that gene expression changes significantly as the worms die (p\u3c0.05), indicating that N. lobata may interrupt the biology of B. pahangi at the gene expression level. The bioinformatics pipeline established for the analysis of this data is able to detect global changes in gene expression in adult female B. pahangi over time
- …
