Safety and Reliability in AI Systems 

This programme focusses on the interplay between generalization and robustness in machine learning. You will examine how these concepts impact model performance and uncover the crucial trade-offs between accuracy and robustness during model development and deployment. 

What you will learn: 

• How generalization affects machine learning model robustness. 
• Key factors in the robustness-accuracy trade-off. 
• The relationship between model performance and reliability. 
• How to apply robustness principles to enhance ML model design. 
• How to evaluate trade-offs in AI safety and deployment decisions. 

Follow the ‘go to course’ and sign up!