Starting Up

Digital Revolution

Emerging Technologies

Cybersecurity

Essence of Agile

Regenerative Farming

Rethinking Health

AI for built environment

How to have difficult conversations

Introduction to inclusivity for knowledge workers

Focus training for knowledge workers

Feedback for self-organizing teams

Facilitation as a skill for forward looking teams

How not to burn out in the tech industry

Trustworthy AI

Advanced trustworthy AI

Elements of AI for Business

Tekoälytyökalut työn tehostajina

In this chapter, we’ll take a deeper dive into the tools that enable trustworthy AI and provide pointers for businesses that want to implement or advance trustworthiness.

advanced-chapter1

Trustworthy AI requirements in practice

Developing trustworthy AI in an organization

Trustworthy AI in organizations and industrial environments

In this chapter, we dive deeper into the concepts of bias, discrimination, and fairness in the machine learning domain. Further, you’ll learn about the different types of biases and how they might slip into AI models. AI unfairness is a concerning societal issue and has many interpretations and definitions. To measure and describe these challenges, various fairness metrics can be useful. Thus, in this chapter, you’ll also learn to use these metrics to detect model unfairness and the ways to mitigate it.

advanced-chapter2

Sources of bias in the evaluation methods for fairness

Methods for assessing and documenting model bias and fairness

Tools for evaluating fairness in your AI model

Bias and fairness in AI

Chapter 3 will give you the knowledge and tools to unpack the functioning and logic of machine learning, the key goal of explainable AI. We start by differentiating between glass box and black box AI algorithms so that you can better understand when and why XAI is needed. We’ll cover different XAI methods that can be used to extract information from AI models. We then explore how these methods work in practice, and give you some guidelines on how to interpret their outputs.

advanced-chapter3

Glass-box and black-box AI – what’s the difference?

Instrumenting AI models with XAI

Applied explainable AI

Interpreting outputs

Dissecting the internal logic of machine learning

In this chapter, we’ll introduce the typical security and privacy attacks made on existing AI systems as well as their corresponding defense strategies. The aim is to understand some typical technical solutions to mitigate security and privacy attacks. Finally, through the presentation of industrial use cases, we show how these solutions are applied in practice. 

advanced-chapter4

Attacks against machine learning systems 

Technical solutions to mitigate attacks

Industry examples of privacy and security

Resilient AI: Defense from security & privacy attacks

In this chapter, you’ll use everything you’ve learned to audit a nascent AI project’s trustworthiness. Finally, we’ll discuss how to communicate effectively about trustworthiness in an organization.

advanced-chapter5

Interactive case: Trustworthiness of service recommendation AI

Epilogue

Conclusion

References

Learn the principles, methods, and tools for implementing trustworthy AI in practice.

Advanced Trustworthy AI