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

Filteren

Zoekresultaten (20)

HBO/WO

MBO

15 juni 2015

Robustness of infrastructures: meaning and use of graph theory for measuring

The first part of this OER focuses on the definition of robustness with the grid as running example. The second part concerns how to measure robustness by using the graph theory . Learning objectives: • To understand the meaning of robustness and resilience within the context of a physical infrastructure or a network (e.g. an electricity grid). • To be able to describe how particularly graph/network theory can be used to quantitatively measure the robustness and resilience of a physical infrastructure or network.

Video

P.F.A. van Mieghem

23 augustus 2023

Lecture: Security and robustness

Gain a general overview of the main security problems of machine learning Understanding the main confidentiality, integrity, and availability issues of machine learning Distinguishing evasion, poisoning and backdoors attacks Understanding clean-label poisoning attacks Obtain the the intuition of adversarial examples and its practical impact through real-life examples Demonstrating the availability attacks by artificially constructed sponge examples Understanding the threat of explainability evasion Understanding the trade-off between robustness and model quality Learn the principles of AI (robustness) auditing

Website

HCAIM Consortium

1 januari 2020

Conceptual Differences of Risk, Resilience and Robustness

This is a game/exercise called “battle of concepts” to differentiate the concepts of resilience, robustness and risk. In this exercise, lecturer presents on the slide the definition or a case study description without indicating what the definition or a case study stands for, all of the students vote for the answers using a personal response system. In this lecture, lecturer distributes an a4 paper as a personal response system, with 3 different shapes representing risk, robustness, resilience. The main advantage of this learning activity is that each student has to read a concept and come up with an answer which makes sure that all students participate in the activity. In addition, the results lead to a debate between the students who give different answers to the presented question. In this activity, lecturer catalyses and manages the brainstorming activity between the students. Lecturer also has an opportunity here to understand the student’s level. In the end, lecturer reveals the result. The main disadvantage of this activity is that it might take quite a long time unexpectedly. Some questions might create a momentum between the students which might lead to a fruitful discussion/debate on certain question.

Document

Nazli Yonca Aydin

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

9 oktober 2024

Resilience of socio-technical-environmental systems

Nazli Aydin introduces an open educational resource designed to teach students the conceptual differences between risk, resilience, and robustness.

Video

Nazli Aydin

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

2 november 2020

Course on Robust Policies for Operations Management Problems

This publication concerns the overview and lecture notes for the course Robust policies for operations management problems. For all other materials, please check the resources (part 1-5) and the links to the web lectures. Societal and industrial parties are facing uncertainties in demands, costs, and many more parameters on which their revenues based. So, the important question is: how companies are making decisions while many of the decision parameters are uncertain? In this resources related to this course we will learn how to answer this question from the perspective of “robustness". This is concept that helps us to make decisions that are not vulnerable to the changes in the uncertain parameters. So, most important concept that will be discussed is: Robustness in Optimization problems. Robustness is critical, especially in making strategic and tactical decisions, which are the decisions that are optimal for a long time. Furthermore, it is important to know how the companies should react to the realization of an uncertain parameter. For instance, what companies should do when the demand is known, the prices are set, the weather condition is known, and etcetera. Learning objectives: Different ways of formulating optimization problems Robust decisions methods to solve or approximate the formulated optimization problems Apply these methods to Operation Management problems and real-life cases. This course consists of 5 modules: -Module 1: Introduction and motivation 1.A: Lecture: Introduction 1.B: Lecture Motivation -Module 2: Static robust optimization 2.A: Robust Conterpart 2.B: Vertex enumeration 2.C: Robust Facility Location 2.D: Uncertainty set Selection -Module 3: Adaptive robust optimizationo What the idea behind Finite Adaptibility is and how to formulate it mathematically. 3.A: Adaptivity in optimization - Adaptive robust optimization - •Difference with (static) RO 3.B: Finitely adaptability 3.C: Affine decision rules 3.D: Finite scenario approach -Module 4: Robust optimization with integer variable 4.A: Lecture 4.B: Excercise and solutions -Module 5: Art of modeling

Document

Ahmadreza Marandi

1 februari 2021

Course Agent Based Modeling

Understanding Complex Adaptive Systems requires tools that themselves are complex to create and understand. Shalizi defines Agent Based Modelling as “An agent is a persistent thing which has some state we find worth representing, and which interacts with other agents, mutually modifying each other’s states. The components of an agent-based model are a collection of agents and their states, the rules governing the interactions of the agents and the environment within which they live.” This course contains 12 chapters. Firstly, an introduction to Complexity and to Agent based modelling is given (chapter 1 and 2). In the next chapters, complex system properties are explained in more detail (chapter 3-7 :Emergence, Path dependence, Adaptiveness, Chaos and instability, Diversity and Self-similarity). Subsequently, in chapter 8, an introduction is given of Robustness and Resilience. Lastly, in chapter 9-12, four other concepts are explained to understand the agent based modelling of complex adaptive systems: Evolution, Network theory and observer dependence. The course can be found on the following link: https://ocw.tudelft.nl/courses/agent-based-modeling-of-complex-adaptive-systems-basic/ This publication also includes various examples (selected research articles) of the use of ABM when it comes to understanding and analyzing resilience. A course summary is also part of the resources. This course relates to the collection "Measuring and Analyzing Resilience of STE Systems."

Website

Ivo Bouwmans, Igor Nikolic

2 november 2020

Course on Robust Policies for Operations Management Problems: Module 1 - Sources of Uncertainty, Probability Theory and its Limitations

This resource concerns module 1 of the course 'Robust policies for operations management problems'. The resources consist of 2 PPT's and the related web -lectures. Learning objectives Sources of uncertainty Limitation of working with average values Limitation of working with chance constraints Why we should use Robust Optimization The material is designed for MSc students in the field of Operations Management. To understand the material, basic knowledge on linear algebra as well as linear optimization is required. Note that the powerpoint version may differ slightly from the PDF version. Please consult the PDF for the original content.

Presentatie

Ahmadreza Marandi

18 februari 2022

The resilience of European farms: A qualitative and quantitative assessment

Short summary of my PhD thesis

Video

edumedia@wur.nl