Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Interpreting Deep Neural Networks Towards Trustworthiness

Alan Turing Institute via YouTube

Overview

Explore a comprehensive conference talk on interpreting deep neural networks for trustworthiness. Delve into the challenges of interpretability in complex machine learning models and discover the agglomerative contextual decomposition (ACD) method for interpreting neural networks. Learn how ACD attributes importance to features and feature interactions, bringing insights to NLP and computer vision problems while improving generalization. Examine the extension of ACD to the frequency domain and the development of adaptive wavelet distillation (AWD) for scientific interpretable machine learning. Understand AWD's applications in cosmology and cell biology predictions. Discuss the importance of quality control throughout the data science lifecycle for building trustworthy interpretable models. Gain valuable insights from Bin Yu of the University of California on advancing the field of interpretable and trustworthy artificial intelligence.

Syllabus

Interpreting deep neural networks towards trustworthiness - Bin Yu, University of California

Taught by

Alan Turing Institute

Reviews

Start your review of Interpreting Deep Neural Networks Towards Trustworthiness

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.