18,404 research outputs found
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
No full textThis 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
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
vsoch/zenodo-ml: Zenodo Machine Learning Dataset, Version 1.0.0
No full text<p>The data is available as a squashfs (read only) file system (the user can download and then mount):</p>
<pre><code>wget https://storage.googleapis.com/dinosaur-datasets/zenodo-ml/zenodo-ml.sqsh
</code></pre>
<p>And full instructions for doing so are provided here <a href="https://vsoch.github.io/datasets/2018/zenodo/#tutorial">https://vsoch.github.io/datasets/2018/zenodo/#tutorial</a></p>
<p>Example analyses (that will continue to be written) are provided in the repository. This version 1.0 represents a first release of the data linked above.</p>
Read-trough efficiency at UGA, UAG and UAA premature stop codons mediated by Gentamicin.
No full textYeast transformants with a plasmid harboring each of the nonsense or the correspondent sense codon, were prepared and cultivated in quadruplicates as described (Fig 4), in the absence or presence of aminoglycoside gentamicin, added at 200 μg/ml (lanes 2, 5 and 8) or 400 μg/ml (lanes 3, 6 and 9. A) Shown is a representative image of yEGFP acquired by a Typhoon 9600 FLA after 19h incubation at 30°C related to a gentamicin mediated read-through assay at the UGA stop codon (see also S2 Fig). B) Read-through percentage is calculated as described in the Materials and Methods. Data are expressed as mean values and indicated with standard deviation.</p
Fibertools: fast and accurate m6A calling using single-molecule long-read sequencing (ML data)
No full textFibertools is a convolutional neural network that permits the fast and accurate identification of endogenous and exogenous N6-methyladenine (m6A)-marked bases using single-molecule long-read sequencing. This dataset (ML data) provides training and validation data for training fibertools supervised and semi-supervised CNN models for three long-read chemistries
RRS Discovery Cruise 351, 10-28 May 2010. The Extended Ellett Line 2010.
No full textThe Extended Ellett Line is a full-depth hydrographic section between Iceland, 60°N 20°W, Rockall and Scotland. The original Ellett Line across the Rockall Trough was first occupied in 1975 when measurements were attempted four times a year. In 1996 the line was extended to Iceland and occupied approximately annually. The data form a 35 year time-series of the oceanic conditions west of the British Isles.The section monitors the characteristics of the warm water inflow into the Nordic Seas and thence to the Arctic, and observes part of the returning cold water outflow with measurements of the Iceland-Scotland Overflow and the overflow of the Wyville-Thomson Ridge into the Rockall Trough.The 2010 occupation, RRS Discovery Cruise 351, was completed successfully with 48 CTD stations worked between the Iceland and Scotland shelf edges. Additionally, Line G, part of the SAMS observation network of the Scottish continental shelf was completed. Samples were taken for inorganic nutrients, iron and trace metals, bioluminescence and microscope analysis. Incubation experiments were performed to investigate the role of microzooplankton grazing and the speciation of iron, and to investigate the presence of dinoflagellate bioluminescence.In addition to the planned programme, sampling took place to investigate the extent of the fall out from the ash plume emitted by the Iceland volcano, Ejyafjallajokull, and its impact on the biogeochemistry and productivity of the upper ocean.A trial tow of SeaSoar and a short survey of the upper ocean over the Anton Dohrn seamount were successfully completed
Read-through efficiency at UGA, UAG and UAA premature stop codons mediated by aminoglycoside G418 determined by YEpRG dual fluorescent reporters.
No full textYeast transformants harboring the YEpRG series (Figs 1B and 3), bearing each UGA, UAG or UAA premature stop codon, or the corresponding sense codon controls, inserted between the yEmRFP and yEGFP ORFs were grown in liquid selective medium and inoculated in quadruplicate in 96 wells microplates in the absence or presence of G418 (8–16 μg/ml). Dual fluorescence was acquired as in Fig 2 (see also text). A) Shown is a representative image of yEGFP acquired by a Typhoon 9600 FLA after 19h incubation at 30°C related to a G418 mediated read-through assay at the UGA stop codon. G418 was added at 8 μg/ml (lanes 2, 5 and 8) or 16 μg/ml (lanes 3, 6 and 9) (primary data and experimental scheme are available in the Supporting Information (S2 Fig). B) Read-through percentage is calculated as described in the Materials and Methods. Data are expressed as mean values and indicated with standard deviation.</p
Building a generalisable ML pipeline at ING
No full textAdvances in data science have caused an increase in the use of Artificial Intelligence (AI), specifically Machine Learning (ML), throughout various fields. Not only in research but in the industry as well, has ML been receiving increasing amounts of interest. Many companies rely on ML models to increase the efficiency of existing processes or offer new services and products. The industry, however, is facing several additional challenges compared to the academic context. One of those challenges is applying the Development Operations (DevOps) model to an ML application, also referred to as MLOps. This thesis sets out to find the specific challenges that practitioners encounter while operationalising ML models. To do so, we perform a single-case case study on an ML pipeline built by the Trade & Communication Surveillance team at the ING bank. This case study consists of conducting a set of interviews and performing a manual code inspection of the pipeline. The team faces challenges ranging from having insufficient time for operationalising each ML project individually to operating in the highlyregulated fintech context. Their pipeline is able to deploy a single ML model but it does not generalise well to other projects. We present the first version of an application that mitigates these challenges. The application is able to deploy ML models to the development environment at ING and can be operated by data scientists to reduce the effort of operationalising an ML model. Computer Science | Software Technolog
The XBabelPhish MAGE-ML and XML Translator
No full textAbstract Background MAGE-ML has been promoted as a standard format for describing microarray experiments and the data they produce. Two characteristics of the MAGE-ML format compromise its use as a universal standard: First, MAGE-ML files are exceptionally large – too large to be easily read by most people, and often too large to be read by most software programs. Second, the MAGE-ML standard permits many ways of representing the same information. As a result, different producers of MAGE-ML create different documents describing the same experiment and its data. Recognizing all the variants is an unwieldy software engineering task, resulting in software packages that can read and process MAGE-ML from some, but not all producers. This Tower of MAGE-ML Babel bars the unencumbered exchange of microarray experiment descriptions couched in MAGE-ML. Results We have developed XBabelPhish – an XQuery-based technology for translating one MAGE-ML variant into another. XBabelPhish's use is not restricted to translating MAGE-ML documents. It can transform XML files independent of their DTD, XML schema, or semantic content. Moreover, it is designed to work on very large (> 200 Mb.) files, which are common in the world of MAGE-ML. Conclusion XBabelPhish provides a way to inter-translate MAGE-ML variants for improved interchange of microarray experiment information. More generally, it can be used to transform most XML files, including very large ones that exceed the capacity of most XML tools.</p
- …
