Agata Lapedriza, a principal research scientist at our Institute, presented her Expeditions in Experiential AI Seminar "Explainable AI in Computer Vision" on Wednesday, May 15, 2024 at Northeastern University's Curry Student Center and online.

In her talk, Agata discusses:
🖥️ The history of computer vision
🎯 Goals and examples of Explainable AI
📊 How Explainable AI can be used to reveal bias in #data

Check out Agata's slides here: https://bit.ly/4avmccy

Abstract:
The goal of Explainable AI is to make AI systems and their decisions transparent and comprehensible to humans. This involves deploying different methodologies and techniques that provide insights on how the AI models work. For example, how they represent the information and how they establish the connections between the inputs and their corresponding outputs. In this talk, Agata focused specifically on Computer Vision. She briefly reviewed the history of this field and presented different approaches that she has explored, such as Unit Interpretability and Class Activation Maps. Agata showed examples of Explainable AI applied to object recognition, action recognition, place categorization, and face classification. Finally, she discussed how Explainable AI can be used to reveal bias in the data that has been encoded in the model during training.

Find out more about The Institute for Experiential AI: https://ai.northeastern.edu/

Connect with us on
LinkedIn:   / eai-nu  
Facebook:   / experientialai  
X: https://x.com/Experiential_AI