Person
Suraj Srinivas
This person is no longer with EPFL
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Related publications (3)
Please note that this is not a complete list of this person’s publications. It includes only semantically relevant works. For a full list, please refer to Infoscience.
Gradient-based Methods for Deep Model Interpretability
In this dissertation, we propose gradient-based methods for characterizing model behaviour for the purposes of knowledge transfer and post-hoc model interpretation. Broadly, gradients capture the variation of some output feature of the model upon unit vari ...
EPFL2021Full-Gradient Representation for Neural Network Visualization
François Fleuret, Suraj Srinivas
We introduce a new tool for interpreting neural net responses, 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 p ...
2019Knowledge Transfer with Jacobian Matching
François Fleuret, Suraj Srinivas
Classical distillation methods transfer representations from a “teacher” neural network to a “student” network by matching their output activations. Recent methods also match the Jacobians, or the gradient of output activations with the input. However, thi ...
2018