21,558 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
Total synthesis of TAN-1057 and analogues
No full text1997 Spring.Includes bibliographical references.Part I. An asymmetric and stereochemically unambiguous construction of diaminopimelic acid and related system using the chiral, non-racemic diphenyl oxazinones glycinate templates has been developed. The preparations of (R,R)-DAP, (S,S)-DAP, (S,S)-2,7-diaminosuberic acid, and mono-N-protected (S,R)-DAP are described. The synthesis of γ-D(L)-glutamyl-L-meso-diaminopimelic acid dipeptide, a subunit of both FK-156 and FK-565, is also described. The availability of both optical antipodes of the glycinate templates renders this chemistry adaptable to prepare all possible diastereoisomers of substances based on the DAP skeleton in optically pure form.Part II. The first total synthesis of anti-MRSA dipeptides TAN-1057 A~D has been achieved. A new efficient method for preparation of amidinoureas has been developed and successfully applied to the total synthesis of TAN-1057. More importantly, this concise total synthesis paves the way for access to analogues that are not available from natural sources. Eight new analogues of TAN-1057 were designed, synthesized and assayed against MRSA. A new synthetic analogue 102 (CY-1800) showed very similar activity to that of TAN-1057. Other analogues prepared showed weak or no activity against Staphylococcus aureus up to 1 mg/mL. The success on discovery of a new potent anti-MRSA analogue proved the usefulness of this highly flexible strategy for the development of better analogues than the natural ones for the potential use as antibiotics
Designing ML-resilient locking at register-transfer level
No full textVarious logic-locking schemes have been proposed to protect hardware from intellectual property piracy and malicious design modifications. Since traditional locking techniques are applied on the gate-level netlist after logic synthesis, they have no semantic knowledge of the design function. Data-driven, machine-learning (ML) attacks can uncover the design flaws within gate-level locking. Recent proposals on register-transfer level (RTL) locking have access to semantic hardware information. We investigate the resilience of ASSURE, a state-of-the-art RTL locking method, against ML attacks. We used the lessons learned to derive two ML-resilient RTL locking schemes built to reinforce ASSURE locking. We developed ML-driven security metrics to evaluate the schemes against an RTL adaptation of the state-of-the-art, ML-based SnapShot attack
Prospective validation of %p2PSA and the Prostate Health Index, in prostate cancer detection in initial prostate biopsies of Asian men, with total PSA 4-10 ng ml-1
No full textDespite its widespread use for prostate cancer screening, low specificity makes PSA a suboptimal biomarker, especially in the diagnostic "gray zone" of 4-10 ng ml-1 . False-positives lead to unnecessary biopsies with attendant morbidities. This is the first prospective validation study of %p2PSA and the Prostate Health Index (PHI) in Asian men presenting with a total PSA between 4.0 and 10 ng ml-1 . We studied 157 Asian men between 50 and 75 years old, with normal per rectal prostate examinations, undergoing their first prostate biopsy, using a standardized biopsy protocol, for PSA levels of 4-10 ng ml-1 . Thirty (19.1%) were found to have prostate cancer on biopsy. Statistically significant differences between patients with and without prostate cancer were found for total PSA, p2PSA, %p2PSA, and PHI. The areas under the curve of the receiver operating characteristic curve for total PSA, %fPSA, %p2PSA, and PHI were 0.479, 0.420, 0.695, and 0.794, respectively. PHI predicts prostatic biopsies results best. At a sensitivity of 90%, the specificity (95% CI) of PHI was 58.3%, more than triple the specificity of total PSA at 17.3%, potentially avoiding 77 (49%) unnecessary biopsies. Similar to studies in mainly Caucasian populations, we have prospectively shown that %p2PSA and PHI greatly outperform total and free to total PSA ratio, in the detection of prostate cancer at first biopsy. Higher PHI levels also correspond to increasing the risk of detecting GS ≥7 cancers. We have validated the use of PHI to aid decision-making regarding prostate biopsies in Asian men with serum PSA between 4 and 10 ng ml-1
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
Involvement of matrix metalloproteinase-13 in stromal-cell-derived factor-1α (SDF-1α)-directed invasion of human basal cell carcinoma cells
No full textAudiomobiles, 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)
- …
