12,444 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
Music for classical guitar by South African composers : a historical survey, notes on selected works and a general catalogue
No full textIncludes abstract.Includes bibliographical references (leaves 296-309).This is the first comprehensive investigation of music for, or including, the classical guitar by South African composers. The focus of this research has been, firstly, to uncover as much of the repertoire as possible, and, secondly, to collate, study, catalogue and report on the information. A brief historical survey of the guitar in South Africa provides the context within which this study was conducted. The primary sources of quantitative data collection were through the archival catalogues of the South African Music Rights Organisation and through personal contact with guitarists, composers and guitar teachers. Other sources consulted were publishers, broadcasting corporations, recording companies, libraries and the internet. The body of the dissertation comprises biographical sketches, background notes, analyses and technical notes on 17 selected solo and chamber works dating from 1947 to 2007 by some of South Africa's most prominent composers and guitaristcomposers. The repertoire ranges in style from the traditional and ethnically inspired to the experimental and abstract. As this is an empirical survey, each selected entry includes details on instrumentation, duration, level of difficulty, number of pages, scordatura, commissions or requests, sources or publishers, premières and recordings. A biography of each composer is provided as well as background notes which offer an overview of the selected work. The notes discuss historical, cultural, musical and extra-musical influences, and frequently include references to interview material. The commentaries on the selected works, with musical examples, include an analytical component describing structure, form, stylistic and compositional elements, while the technical observations include performance suggestions and a grading for each work
ML-Driven DASH Content Pre-Fetching in MEC-Enabled Mobile Networks
No full textStreaming high-quality video over dynamic radio networks is challenging. Dynamic adaptive streaming over HTTP (DASH) is a standard for delivering video in segments, and adapting its quality to adjust to a changing and limited network bandwidth. We present a machine learning-based predictive pre-fetching and caching approach for DASH video streaming, implemented at the multi-access edge computing server. We use ensemble methods for machine learning (ML) based segment request prediction and an integer linear programming (ILP) technique for pre-fetching decisions. Our approach reduces video segment access delay with a cache-hit ratio of 60% and alleviates transport network load by reducing the backhaul link utilization by 69%. We validate the ML model and the pre-fetching algorithm, and present the trade-offs involved in pre-fetching and caching for resource-constrained scenarios
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
Effects of dense phase carbon dioxide pasteurization on the physical and quality attributes of a red grapefruit juice
No full textABSTRACT: Red grapefruit juice was treated with continuous dense phase carbon dioxide (DPCD) equipment to
inactivate yeasts and molds and total aerobic microorganisms. A central composite design was used with pressure
(13.8, 24.1, and 34.5 MPa) and residence time (5, 7, and 9 min) as variables at constant temperature (40 ◦C), and
CO2 level (5.7%) after experimentallymeasuring CO2 solubility in the juice. Five log reduction for yeasts and molds
and total aerobicmicroorganisms occurred at 34.5 MPa and 7 min of treatment. A storage study was performed on
the fresh juice DPCD treated at these conditions. ◦Brix, pH, titratable acidity (TA), pectinesterase (PE) inactivation,
cloud, color, hue tint and color density, total phenolics, antioxidant capacity, and ascorbic acid weremeasured after
the treatment and during 6 wk storage at 4 ◦C. During storage, the DPCD-treated juice showed no growth of total
aerobic microorganisms and yeasts and molds. Cloud increased (91%) while percent PE inactivation was partial
(69.17%). No significant (α = 0.05) differences were detected between treated and untreated samples for ◦Brix, pH,
and TA. Treated juice had higher lightness and redness and lower yellowness. No significant differences (α = 0.05)
were detected for the hue tint values while the color density value was higher for the treated samples compared to
the untreated. The treatment and the storage did not affect the total phenolic content of the juice. Slight differences
were detected for the ascorbic acid content and the antioxidant capacity. The experimental results showed evidence
that the treatment canmaintain the physical and quality attributes of the juice, extending its shelf life and safety
ML-Driven DASH Content Pre-Fetching in MEC-Enabled Mobile Networks
No full textStreaming high-quality video over dynamic radio networks is challenging. Dynamic adaptive streaming over HTTP (DASH) is a standard for delivering video in segments, and adapting its quality to adjust to a changing and limited network bandwidth. We present a machine learning-based predictive pre-fetching and caching approach for DASH video streaming, implemented at the multi-access edge computing server. We use ensemble methods for machine learning (ML) based segment request prediction and an integer linear programming (ILP) technique for pre-fetching decisions. Our approach reduces video segment access delay with a cache-hit ratio of 60% and alleviates transport network load by reducing the backhaul link utilization by 69%. We validate the ML model and the pre-fetching algorithm, and present the trade-offs involved in pre-fetching and caching for resource-constrained scenarios
MD simulations and ML dataset of HLA-EpiCheck epitope predictor tool
No full textThis dataset contains all the data used to implement the B-cell epitope predictor tool called HLA-EpiCheck (see https://doi.org/10.1101/2023.12.18.572133).
CONTENTS:
- pre-patches: Directory containing the computed pre-patches. A pre-patch corresponds to the set of residues within a given distance from a residue. The patches are generated subsequently by keeping only the solvent-accessible residues. Files are organized by locus and by antigen. A file contains the pre-patches associated to a given residue computed for any frame considered in the trajectory.
+ _patches_resid__size_.txt:
Each line in the file corresponds to a pre-patch of a given frame.
Line format : :
Residue numbering is the same as in the PDB files.
- trajectories: Directory contaning the MD data. Files are organized by locus and by antigen.
+ .dcd: 10ns MD trajectory comprising 1000 frames. Water molecules were removed.
+ .psf: Topology file of the .dcd trajectory.
+ .pdb: Starting structure of the MD simulation.
- training_set_size_15.csv: training set used to train HLA-EpiCheck.
- test_set_size_15.csv: test set used to evaluate HLA-EpiCheck.
- table_patch_ID_antigen_residue.csv: Table containing the antigen and central residue associated to each patch.
- model_ERF_radius_15.pkl: ML model of HLA-Epicheck in pickle format. Pickle version 4.0 used.
- descriptors_eplets_non-confirmed.csv: Descriptors of the non-confirmed residue patches.
- preds_non_confirmed_DQ.csv: HLA-EpiCheck predictions on the non-confirmed residue patches of eplets from locus DQ.
- PDB_modeled_structures.txt : List of antigens modeled from a PDB structure with the corresponding PDB entry
'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
- …
