Uber AI, Engineering
Understanding Neural Networks via Feature Visualization: A survey
April 18, 2019 / GlobalAbstract
A neuroscience method to understanding the brain is to find and study the preferred stimuli that highly activate an individual cell or groups of cells. Recent advances in machine learning enable a family of methods to synthesize preferred stimuli that cause a neuron in an artificial or biological brain to fire strongly. Those methods are known as Activation Maximization (AM) or Feature Visualization via Optimization. In this chapter, we (1) review existing AM techniques in the literature; (2) discuss a probabilistic interpretation for AM; and (3) review the applications of AM in debugging and explaining networks.
Authors
Anh Nguyen, Jason Yosinski, Jeff Clune
Publication
Interpretable AI: Interpreting, Explaining and Visualizing Deep Learning
Full Paper
Uber AI
Category:
