Timezone: »

 
Poster
Full-Gradient Representation for Neural Network Visualization
Suraj Srinivas · François Fleuret

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #167
in Deep Learning -- Visualization or Exposition Techniques for Deep Networks »

We introduce a new tool for interpreting neural nets, namely full-gradients, which decomposes the neural net response into input sensitivity and per-neuron sensitivity components. This is the first proposed representation which satisfies two key properties: completeness and weak dependence, which provably cannot be satisfied by any saliency map-based interpretability method. Using full-gradients, we also propose an approximate saliency map representation for convolutional nets dubbed FullGrad, obtained by aggregating the full-gradient components.

We experimentally evaluate the usefulness of FullGrad in explaining model behaviour with two quantitative tests: pixel perturbation and remove-and-retrain. Our experiments reveal that our method explains model behavior correctly, and more comprehensively than other methods in the literature. Visual inspection also reveals that our saliency maps are sharper and more tightly confined to object regions than other methods.

Keywords: Supervised Deep Networks · Visualization or Exposition Techniques for Deep Networks · Deep Learning · Applications -> Computer Vision; Deep Learning
[ Paper]  [ Poster] 

Author Information

Suraj Srinivas (Idiap Research Institute & EPFL)

I'm a 3rd year PhD student who is interested in interpretability and regularization methods for deep neural networks. I am also interested in issues relating to causality, transfer learning and mathematics of deep learning.

François Fleuret (Idiap)

François Fleuret got a PhD in Mathematics from INRIA and the University of Paris VI in 2000, and an Habilitation degree in Mathematics from the University of Paris XIII in 2006. He is Full Professor in the department of Computer Science at the University of Geneva, and Adjunct Professor in the School of Engineering of the École Polytechnique Fédérale de Lausanne. He has published more than 80 papers in peer-reviewed international conferences and journals. He is Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence, serves as Area Chair for NeurIPS, AAAI, and ICCV, and in the program committee of many top-tier international conferences in machine learning and computer vision. He was or is expert for multiple funding agencies. He is the inventor of several patents in the field of machine learning, and co-founder of Neural Concept SA, a company specializing in the development and commercialization of deep learning solutions for engineering design. His main research interest is machine learning, with a particular focus on computational aspects and sample efficiency.

More from the Same Authors