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

Filteren

Zoekresultaten (13)

HBO/WO

MBO

8 april 2026

ACA-bot

ACA-bot is an engaging chatbot designed for Automated Conversational Assessment (ACA). Drawing inspiration from traditional oral exams, this text-based conversational agent transforms assessment into a dynamic learning experience. It supports both formative and summative evaluation by offering students personalised feedback and guidance at every step of their learning journey. The first ACA-bot prototype focuses on assessing students’ understanding of basic statistical concepts, but its flexible design allows for easy adaptation to a wide range of subjects and learning contexts. Through interactive dialogue, students can practise explaining ideas clearly under exam-like conditions, apply their knowledge to new and challenging questions, and refine their reasoning as they respond to follow-up prompts. They gain valuable insights into their own understanding, identify areas for improvement, and gradually build confidence for both oral and written assessments. For educators, ACA-bot offers a powerful way to scale oral examinations and enhance formative assessment without increasing workload. It automates parts of the assessment process, provides structured and actionable insights into student performance, and opens the door to more personal, interactive feedback at scale. By combining the strengths of conversational AI and educational assessment, ACA-bot turns evaluation into a collaborative, insightful process. It empowers students to think aloud, reason more effectively, and grow, while giving educators a smarter, more innovative way to understand and support learning. ACA-bot is een slimme en inspirerende chatbot die onderwijs en Artificial Intelligence samenbrengt. Geïnspireerd door het klassieke mondelinge examen tilt deze tekstgebaseerde gespreksagent Automated Conversational Assessment naar een nieuw niveau. Studenten krijgen via natuurlijke gesprekken directe, persoonlijke feedback en begeleiding, waardoor leren en toetsen samenvloeien in één boeiende ervaring. Het prototype van ACA-bot is ontwikkeld om kennis over statistiek te beoordelen, maar dankzij het flexibele ontwerp kan het systeem eenvoudig worden aangepast aan andere vakgebieden en toepassingen. Tijdens interactieve dialogen leren studenten helder uitleg geven, hun kennis toepassen op nieuwe vragen en hun redenering aanscherpen. Ze ontdekken waar hun begrip nog verdiept kan worden en groeien zichtbaar in zelfvertrouwen — waardevolle voorbereiding op zowel mondelinge als schriftelijke examens. Ook voor docenten biedt ACA-bot een slimme oplossing. Het maakt mondelinge toetsing schaalbaar, ondersteunt formatieve beoordeling via gesprek, en vermindert de werkdruk door delen van het beoordelingsproces te automatiseren. Bovendien geeft het gestructureerde inzichten in de voortgang en denkwijze van studenten, waardoor elke dialoog bijdraagt aan beter onderwijs. ACA-bot laat zien hoe Automated Conversational Assessment het leren persoonlijker, interactiever en effectiever maakt. Studenten denken hardop, verkennen hun eigen begrip, en verbeteren met vertrouwen — terwijl docenten op een innovatieve, datagedreven manier inzicht krijgen in hoe kennis werkelijk wordt begrepen.

App

Aki Härmä, Julie Bauer

23 augustus 2023

Lecture: Decision Trees

Learn basics of decision trees

Website

HCAIM Consortium

23 augustus 2023

Practical: Decision Trees

Learners understand the MLP architectre Learners can construct neural networks with fully connected layers and various activation functions Learners understand the basic idea of backpropagation and gradient-based methods

Website

HCAIM Consortium

23 augustus 2023

Lecture: Batch processing

Understand mechanisms behind batch processing and back propagation Gradient Descent, Batch vs MiniBatch vs Epoch

Website

HCAIM Consortium

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

23 augustus 2023

Practical: Apply auditing frameworks

Gain practical skills how to audit the robustness of machine learning models How to implement evasion (adversarial examples) and poisoning/backdoor attacks Evaluate the model degradation due to these attacks

Website

HCAIM Consortium

23 augustus 2023

Lecture: ML-Ops Lifecycle

Understanding MLOPs end-to-end Understanding Data Ingestion Getting familiar with Algorithm Development Getting familiar with Model Development and Deployment Understanding Continuous Monitoring

Website

HCAIM Consortium

23 augustus 2023

Practical: SVMS and Kernels

To be able to design and use a linear SVM To be able to design ad use a non-linear SVM, using a kernel To design and optmize a SVM (cookbook approach)

Website

HCAIM Consortium

23 augustus 2023

Tutorial: Model Evaluation

Learners understand the concept of expected predictive performance and generalization Learners understand the concept of model complexity and its relationship with generalization performance Learners are familiar with bias and variance their relationship with underfitting and overfitting Learners have a firm grasp on evaluating binary classification models with the most widely applied metrics

Website

HCAIM Consortium

23 augustus 2023

Interactive session: Risk & Risk mitigation

Recognize, analyze and discuss the necessity and the role of security testing in AI. Employ documents, such as the AI Act, to classify use cases into risk categories. Discuss in-depth and with common European vocabulary on AI risk and how can AI be designed safely and benevolently, in ways that will not expose humans to unacceptable risks of harm, even when risky behaviour may advance a system goal. Classify the obligations of providers and users in relation to AI risk management. Discuss the requirements for high-risk AI systems as per the AI Act. Elaborate and recognize specific risks and risk taxonomies, relevant throughout the different stages of the AI lifecycle.

Website

HCAIM Consortium