All videos
All videos
Explaining neural networks predictions
April 16, 2018
Recently Deep Neural Networks have become superior in many machine learning tasks. However, they are more difficult to interpret than simpler models like Support Vector Machines or Decision Trees. One may say that neural nets are black boxes that produce predictions but we can’t explain why a given prediction is made. Such a condition is not acceptable in industries like healthcare or law. In this talk, I will show known ways of understanding neural networks predictions.
Tags
Other videos that you might like
Recent advancements in NLP and deep learning: a quant’s perspective
Umit Mert Cakmak
Improving Sentiment Analysis Code in a DevOps environment
Oindrilla Chatterjee
pandas-stubs — How we enhanced pandas with type annotations
Joanna Sendorek, Zbyszek Królikowski
ART 360: Defending AI models against adversarial attacks
Mathieu Sinn