Ga naar de startpagina
Zoek leermateriaalKennis & expertiseCommunities
NL|EN
Privacy policyDeelnemende instellingen
Creative CommonsCreative Commons AttributionSURFFunded by the European Union

Filteren

Zoekresultaten (113)

…

HBO/WO

MBO

23 augustus 2023

Practical: Enhancing ML security and robustness

Gain practical skills to mitigate integrity problems of machine learning Design robust machine learning models Mitigate evasion (adversarial examples) Mitigate backdoors (poisoning) Evaluate the trade-off between robustness and model accuracy

Website

HCAIM Consortium

8 mei 2018

06-01: Scale index construction and assessment - micro lecture checking a measurement instrument

In this micro lecture the following items will be explained regarding this lecture: Introducing the validity (including specificity, sensitivity and accuracy) and the reliability of a measurement instrument

Video

Henk van der Kolk

9 juni 2026

Handout - TR3CA: Evaluation of your (AI-assisted) literature search

These are the Transparency & Reproducibility, Relevancy, Reliability, Coverage, Accuracy (TR3CA) evaluation criteria to evaluate whether results from an (AI-assisted) literature search are trustworthy and appropriate for your research.

Document

Anna-Lena Hoh, Marieke Schor, Floor Ruiter, Candan Yılmaz

23 augustus 2023

Practical: Applying and evaluating privacy-preserving techniques

Gain practical skills to mitigate privacy leakages by applying Differential Privacy How to anonymize datasets with Differential Privacy How to train ML models with Differential Privacy Understanding the difference between data anonymization and privacy-preserving model training Study the trade-off between privacy preservation (anonymization) and utility (model quality, data accuracy)

Website

HCAIM Consortium

14 april 2022

The Rest Is History | 175. Crucifixion (Part 1)

Crucifixions were a form of public execution so heinous that the Romans themselves were reluctant to document their gory details... In this Easter special, Tom and Dominic trace the origins and evolution of crucifixion - as well as the historical accuracy of Jesus' death. Warning: this pod is not for the faint of heart. Producer: Vasco Andrade Exec Producers: Tony Pastor & Jack Davenport

Audio

Tom Holland, Dominic Sandbrook, Vasco Andrade, Tony Pastor, Jack Davenport

23 augustus 2023

Lecture: Introduction General Explainable AI

Understand, analyze and elaborate upon the importance of XAI in the modern world. Differentiate between transparent and opaque machine learning models. Categorize and discuss approaches to explainability XAI based on model scope, agnosticity, data types and explanation techniques. Discern, investigate and discuss the trade-off between accuracy and interpretability. Summarize and understand the working principles and mathematical modeling of XAI techniques like LIME, SHAP, DiCE, LRP, counterfactual and contrastive explanations. Expand on possible applications of XAI techniques like LIME, SHAP, DiCE, LRP to generate explanations for black-box models for tabular, textual, and image datasets.

Website

HCAIM Consortium

2021

Tracking student skills real-time through a continuous-variable dynamic Bayesian network

The field of Knowledge Tracing is focused on predicting the success rate of a student for a given skill. Modern methods like Deep Knowledge Tracing provide accurate estimates given enough data, but beingbased on neural networks they struggle to explain how these estimates are formed. More classical methodslike dynamic Bayesian networks can do this, but they cannot give data on the accuracy of their estimatesand often struggle to incorporate new observations in real-time due to their high computational load.This paper presents a novel method, Performance Distribution Tracing (PDT), in which the distribution of the success rate is traced. It uses a dynamic Bayesian network with continuous random variablesas nodes. By tracing the success rate distribution, there is always data available on the accuracy of any success rate estimation. In addition, it makes it possible to combine data from similar/related skills tocome up with a more informed estimate of success rates. This makes it possible to accurately predictexercise success rates, even when an exercise requires a combination of different skills to solve. Andthrough the use of the right conjugate priors, all distributions are available in analytical form, allowing efficient online updates upon new observations. An application to an engineering physics course has shown that the PDT algorithm works well inreal-life settings. Students mainly appreciate the overview given of their learning process as well as the corresponding practice recommendations.

Document

Hildo Bijl

1 september 2023

Rubrics minor Science, Technology & Innovation: Biomimicry

The rubric for the final report in the UvA's ST&I: Biomimicry minor is designed to assess students' ability to communicate their project findings effectively, integrating technical and scientific research with biomimicry principles. It emphasizes layout, scientific grounding, prototype development, testing accuracy, and comprehensive documentation, aiming to ensure clarity, depth, and professionalism in student reports. This detailed evaluation framework aligns with the program's interdisciplinary and innovative ethos, preparing students for real-world challenges while fostering academic rigor and creativity.

Document

Morten Stromme

22 maart 2019

Epistolae: Medieval Women’s Letters

Epistolae is a collection of medieval Latin letters to and from women. The letters collected here date from the 4th to the 13th centuries, and they are presented in their original Latin as well as in English translation. The letters are organized by the name and biography of the women writers or recipients. Biographical sketches of the women, descriptions of the subject matter of the letters, and the historical context of the correspondence are included where available. Dr. Joan Ferrante, Professor Emerita of English and Comparative Literature of Columbia University, has with her colleagues collected and translated these letters mainly from printed sources. She has worked with the Columbia Center for New Media Teaching and Learning to develop this unique open online collection for teaching and research purposes. New letters continue to be added to the collection. Users are invited to participate by sending material or inquiries to jmf2@columbia.edu. Contributions, fully acknowledged, will be added to the database after review for accuracy and style by members of the Epistolae board.

Website

Joan Ferrante

14 augustus 2023

Citing information: Choose a citation style

Choose a citation style When writing an academic paper, you need to provide references to all the works you cite. You are responsible for checking the accuracy and completeness of these references. Suggested.

Website

Erasmus University Library