16,557 research outputs found

    Metadata Representations for Queryable ML Model Zoos

    No full text
    Machine 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 text
    This 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 text
    The 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

    Isolation, characterization and screening of functional properties probiotic candidates for lactic acid bacteria Bali traditional drink wong tea in vitro

    No full text
    One of the functional foods in Bali, especially in Gianyar Regency, is teh wong (mushroom), which has a sweet-sour taste. The purpose of the study was to determine the characteristics of probiotic candidates isolated from the fermented tea wong drink and to determine the LAB of Teh Wong which could potentially be probiotic candidates. The samples used were 20 lactic acid bacteria (LAB) isolates from wong tea. The process of isolating the LAB candidate used the spread plate method from the fermented liquid of Teh Wong for 7 days. Isolation was carried out after the plates were incubated for 24 hours at 37oC. Colonies suspected of being LAB were then streaked on new De Man, Rogosa and Sharpe (MRS) Agar media to obtain a single colony. The total LAB produced from LAB isolates ranged from 3.0 x 105 cfu/ml to 7.0 x 108 cfu/ml. Of the 20 isolates from gram staining, it was found that the LAB Teh Wong isolate was dominated by rods (bacilli) and only 4 isolates were spherical (coccus)

    Isolation, Characterization and Screening of Functional Properties Probiotic Candidates for Lactic Acid Bacteria BALI Traditional Drink Wong Tea in Vitro

    No full text
    One of the functional foods in Bali, especially in Gianyar Regency, is teh wong (mushroom), which has a sweet-sour taste. The purpose of the study was to determine the characteristics of probiotic candidates isolated from the fermented tea wong drink and to determine the LAB of Teh Wong which could potentially be probiotic candidates. The samples used were 20 lactic acid bacteria (LAB) isolates from wong tea. The process of isolating the LAB candidate used the spread plate method from the fermented liquid of Teh Wong for 7 days. Isolation was carried out after the plates were incubated for 24 hours at 37oC. Colonies suspected of being LAB were then streaked on new De Man, Rogosa and Sharpe (MRS) Agar media to obtain a single colony. The total LAB produced from LAB isolates ranged from 3.0 x 105 cfu/ml to 7.0 x 108 cfu/ml. Of the 20 isolates from gram staining, it was found that the LAB Teh Wong isolate was dominated by rods (bacilli) and only 4 isolates were spherical (coccus)

    Building a generalisable ML pipeline at ING

    No full text
    Advances 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

    'Project smells' - Experiences in Analysing the Software Quality of ML Projects with mllint

    No full text
    Machine Learning (ML) projects incur novel challenges in their development and productionisation over traditional software applications, though established principles and best practices in ensuring the project's software quality still apply. While using static analysis to catch code smells has been shown to improve software quality attributes, it is only a small piece of the software quality puzzle, especially in the case of ML projects given their additional challenges and lower degree of Software Engineering (SE) experience in the data scientists that develop them. We introduce the novel concept of project smells which consider deficits in project management as a more holistic perspective on software quality in ML projects. An open-source static analysis tool mllint was also implemented to help detect and mitigate these. Our research evaluates this novel concept of project smells in the industrial context of ING, a global bank and large software- and data-intensive organisation. We also investigate the perceived importance of these project smells for proof-of-concept versus production-ready ML projects, as well as the perceived obstructions and benefits to using static analysis tools such as mllint. Our findings indicate a need for context-aware static analysis tools, that fit the needs of the project at its current stage of development, while requiring minimal configuration effort from the user. 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.Software EngineeringSoftware Technolog

    Audiomobiles, Sculptures and Conundrums

    No full text
    Roberto Gerhard was a pioneer of electronic music in England creating a number of substantial concert, theatre and radio works from as early as 1954. Gerhard’s electronic music is one of the richest repositories for understanding the development of the composer’s late compositional technique. Apart from the Symphony no.3, ‘Collages’, none of Gerhard’s electronic music is published. This paper will discuss aspects of Gerhard’s electronic music, focusing on Audiomobiles (1958-59) and Sculptures (1963)

    The Antioxidant Content of Wong Lo Kat Tea

    No full text
    Wong Lo Kat (or Wanglaoji in Mandarin) is a popular soft drink containing herbal tea that is often used as a Chinese folk remedy for mild ailments. The herbs included in the drink are the following: Chinese Mesona, White Frangipani, Microcos, Chrysanthemum, Japanese Honeysuckle, Heal All, and Chinese Licorice. While there is research on the individual plants, there is limited information on the combined mixture of the herbs included in the Wong Lo Kat drink, particularly in published English literature. Antioxidant content for the individual herbs and a combined mixture of equal parts of each herb was tested using the TEAC test. To prepare the combined herb solution, each herb’s phenolics were sonicated, centrifuged, and concentrated using a rotary evaporator, then combined in equal parts using 1 mL each. The antioxidant activities were found to be the following: Chinese Mesona was 1.5586 ± 0.1217; White Frangipani was 1.4277 ± 0.2351; Microcos was 1.2813 ± 0.1398; Chrysanthemum was 1.2183 ± 0.1961; Japanese Honeysuckle was 1.4751 ± 0.1702; Heal All was 1.4905 ± 0.1702; Chinese Licorice was 1.1554 ± 0.1483; and combined was 1.2463 ± 0.1892. All values were reported in mmol Trolox equivalency/g sample. ANOVA test was used with Tukey\u27s test to determine that the means of the herbs and combined mixture were not statistically significant from each other. Comparing the Wong Lo Kat mixture with teas available in the market, the antioxidant activity is comparable to several high-quality iterations of green tea and other teas in the market

    Potential of lactic acid bacteria from wong tea can reduce rats' blood serum cholesterol levels

    No full text
    Lactic Acid Bacteria (LAB) isolated from wong tea which have the potential to be probiotic candidates generally have the ability to reduce cholesterol levels. This research uses BAL isolate from wong tea as a probiotic drink that can lower cholesterol. The LAB isolate used is resistant to low pH, resistant to microbial activity (S. aureus and E. coli) and resistant to bile salts. The aim of this research was to determine the effect of giving LAB from wong tea to reduce blood serum cholesterol levels in mice in vitro. The research design used was a Randomized Block Design (RAK) with 5 treatments giving BAL and each treatment was repeated 4 times. Giving BAL for 14 (fourteen) days is carried out in batches. Total LAB was carried out using the surface method on MRS agar, Gram staining using the staining method, cholesterol levels were measured using a cholesterol kit using the CHOD-PAP enzymatic method. The total research results of Wong tea's LAB ranged from 1.23 x 109 to 2.20 x 109 cfu/ml. The isolation process obtained by Gram staining showed positive Gram staining results in the form of rods.&nbsp
    corecore