9,764 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
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
'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
Audiomobiles, Sculptures and Conundrums
No full textRoberto 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)
Chemotherapy for late-stage cancer patients: meta-analysis of complete response rates
No full textComplete response (CR) rates reported for cytotoxic chemotherapy for late-stage cancer patients are generally low, with few exceptions, regardless of the solid cancer type or drug regimen. We investigated CR rates reported in the literature for clinical trials using chemotherapy alone, across a wide range of tumour types and chemotherapeutic regimens, to determine an overall CR rate for late-stage cancers. A total of 141 reports were located using the PubMed database. A meta-analysis was performed of reported CR from 68 chemotherapy trials (total 2732 patients) using standard agents across late-stage solid cancers-a binomial model with random effects was adopted. Mean CR rates were compared for different cancer types, and for chemotherapeutic agents with different mechanisms of action, using a logistic regression. Our results showed that the CR rates for chemotherapy treatment of late-stage cancer were generally low at 7.4%, regardless of the cancer type or drug regimen used. We found no evidence that CR rates differed between different chemotherapy drug types, but amongst different cancer types small CR differences were evident, although none exceeded a mean CR rate of 11%. This remarkable concordance of CR rates regardless of cancer or therapy type remains currently unexplained, and motivates further investigation.Martin L. Ashdown, Andrew P. Robinson, Steven L. Yatomi-Clarke, M. Luisa Ashdown, Andrew Allison, Derek Abbott, Svetomir N. Markovic, Brendon J. Coventr
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
The 20th anniversary of interleukin-2 therapy: bimodal role explaining longstanding random induction of complete clinical responses
No full textBrendon J Coventry, Martin L AshdownDiscipline of Surgery, University of Adelaide, Royal Adelaide Hospital and Faculty of Medicine, University of Melbourne, AustraliaBackground: This year marks the twentieth anniversary of the approval by the US Food and Drug Administration of interleukin-2 (IL2) for use in cancer therapy, initially for renal cell carcinoma and later for melanoma. IL2 therapy for cancer has stood the test of time, with continued widespread use in Europe, parts of Asia, and the US. Clinical complete responses are variably reported at 5%–20% for advanced malignant melanoma and renal cell carcinoma, with strong durable responses and sustained long-term 5–10-year survival being typical if complete responses are generated.Methods: The literature was reviewed for the actions and clinical effects of IL2 on subsets of T cells. The influence of IL2 on clinical efficacy was also sought.Results: The review revealed that IL2 is capable of stimulating different populations of T cells in humans to induce either T effector or T regulatory responses. This apparent "functional paradox" has confounded a clear understanding of the mechanisms behind the clinical effects that are observed during and following administration of IL2 therapy. An average complete response rate of around 7% in small and large clinical trials using IL2 for advanced renal cell carcinoma and malignant melanoma has been shown from a recent review of the literature.Conclusion: This review considers the published literature concerning the actions and emerging clinical effects of IL2 therapy, spanning its 20-year period in clinical use. It further details some of the recently described "bimodal" effects of IL2 to explain the apparent functional paradox, and how IL2 might be harnessed to emerge rapidly as a much more effective and predictable clinical agent in the near future.Keywords: interleukin-2, cancer therapy, immunotherapy, immune response, translational research, cytokines, regulatory T cells, immune modulation, complete responses, bimodal rol
Complete clinical responses to cancer therapy caused by multiple divergent approaches: a repeating theme lost in translation
No full textBrendon J Coventry, Martin L AshdownDiscipline of Surgery, University of Adelaide, Royal Adelaide Hospital and Faculty of Medicine, University of Melbourne, AustraliaAbstract: Over 50 years of cancer therapy history reveals complete clinical responses (CRs) from remarkably divergent forms of therapies (eg, chemotherapy, radiotherapy, surgery, vaccines, autologous cell transfers, cytokines, monoclonal antibodies) for advanced solid malignancies occur with an approximately similar frequency of 5%–10%. This has remained frustratingly almost static. However, CRs usually underpin strong durable 5-year patient survival. How can this apparent paradox be explained?Over some 20 years, realization that (1) chronic inflammation is intricately associated with cancer, and (2) the immune system is delicately balanced between responsiveness and tolerance of cancer, provides a greatly significant insight into ways cancer might be more effectively treated. In this review, divergent aspects from the largely segmented literature and recent conferences are drawn together to provide observations revealing some emerging reasoning, in terms of "final common pathways" of cancer cell damage, immune stimulation, and auto-vaccination events, ultimately leading to cancer cell destruction. Created from this is a unifying overarching concept to explain why multiple approaches to cancer therapy can provide complete responses at almost equivalent rates. This "missing" aspect provides a reasoned explanation for what has, and is being, increasingly reported in the mainstream literature – that inflammatory and immune responses appear intricately associated with, if not causative of, complete responses induced by divergent forms of cancer therapy. Curiously, whether by chemotherapy, radiation, surgery, or other means, therapy-induced cell injury results, leaving inflammation and immune system stimulation as a final common denominator across all of these mechanisms of cancer therapy. This aspect has been somewhat obscured and has been "lost in translation" to date.Keywords: chemotherapy, immunotherapy, immune response, common pathways, translational research, oscillation, regulatory T-cells, immune modulation, complete response
- …
