9,835 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
Tissue damage and haematophagia due to praniza larvae (Isopoda : Gnathiidae) in some aquarium seawater teleosts
No full textOver a 5 yr period, severe infestations due to Gnathia vorax larvae affecting different
teleosts have been registered at the Civic Aquarium of Messina, Italy. Here, the damage caused by
these parasites is evaluated from a macroscopical and histopathological point of view. We also
attempt to evaluate the amount of blood sucked up by a single parasite and make some observations
about the haematophagia. The histopathological changes confirm mucosal electrolytic failure as the
main problem, even though the mean value of blood sucked up by a single parasite, about 1.9 mg,
suggests that haematophagia may play an important role in the pathogenesis of such infestation. In
conclusion, it was found that the G. vorax larvae caused 2-fold damage that was responsible for the
death of the fish. Little by little, the parasitic problem was successfully removed by washing the
tank, using fresh water rather than costly and dangerous chemotherapeutans
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
PSA supernormalisation: a surrogate of complete adenoma removal in men with benign prostatic hyperplasia.
No full textIt is known that serum prostate-specific antigen levels (PSA) decrease gradually following surgery for benign prostatic hyperplasia (BPH), but there is not an established cut-off value for normal PSA after relief of obstruction. We evaluated the impact of prostatic adenoma enucleation on PSA levels in 110 patients who underwent transvesical suprapubic adenomectomy for symptomatic BPH. We examined PSA levels before and after open surgery and weight of the prostatic adenoma as measured by the pathologist. Forty-eight percent of the patients had a preoperative PSA level between 0 and 4, 29% between 4 and 7, and 23% between 7 and 10 ng/ml. In patients with suspected abnormality on digital rectal examination or PSA > 4.0 ng/mL systematic multisite biopsies were performed preoperatively to rule out prostate cancer. The mean weight of enucleated adenoma was 87 gr (range 50-201). The mean serum PSA decreased from 4.8 ng/ml preoperatively to 0.5 ng/ml postoperatively. The mean decrease in PSA was 90% (range 70-99%). PSA was resetted at lower level in all patients irrespectively of baseline PSA levels or BPH weight. The transvesical suprapubic adenomectomy supernormalises serum PSA lower than 1 ng/ml in 96% of patients. 100% of patients have a postoperative PSA value < 1.5 ng/ml. PSA supernormalisation represents an objective measure of complete adenoma removal. The urologists should be aware of this resetted level and they should take account of it when different ablative therapies for BPH are confronted
Effects of coco fibre addition to perlite on growth and yield of cut Gerbera
No full textThe experiment was carried out in Naples during a 12-month period, in a heated glasshouse (set point 12 °C). The effects of the addition of an upper coco fibre layer to perlite on growth and productivity of cut gerbera grown in pot in an open hydroponic system were investigated. Plants of Gerbera jamesonii cultivar Leader were cultivated at the planting density of 5.5 plants per m2 and fertilized via a drip-system. EC and pH of nutrient solution were kept at 1.6 dS m-1 and 6.0 respectively and the number of pulses ranged from 1 (October-January) to 7 (July) per day (400 ml per pulse). The addition of the upper layer of coco fibre to the perlite raised the leaf water potentials (-0.74 vs -0.84 MPa) and the rates of net assimilation (13.7 vs 12.1 mol CO2 m-2 s-1) and transpiration (6.01 vs 5.19 mmol H2O m-2 s-1) of Gerbera plants compared to the perlite only, and higher differences were observed during the warmer months. The substrate significantly influenced the plant growth: plants on perlite +coco fibre had larger leaf area per plant compared to P, due to both the higher leaf number and the larger unitary leaf area, and produced more cut stems (53 vs 44.4 stems per plant), with no significant difference in stem quality between the two substrates. The cumulated water consumption was higher in plants grown with the addition of coco fibre compared to those grown on perlite (71.6 vs 58.9 L plant-1). Chemical analysis revealed a significant higher content of P and K in leaf tissues of plants grown with the addition of the organic medium
Solventi eutettici naturali per la determinazione dei composti fenolici negli oli vergini di oliva
No full textBuilding 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
'Project smells' - Experiences in Analysing the Software Quality of ML Projects with mllint
No full textMachine 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
- …
