SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.13581 · 2021

Gradient representations in ReLU networks as similarity functions

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
danielracz/gradsim canonical 1 of 3
FunctionStatusWhere it lives
test_model Ran danielracz/gradsim/grad_utils.py
pointer only (licence: NONE) · get_code("2ccdbf7196e90927")
get_data Not yet run danielracz/gradsim/grad_utils.py
pointer only (licence: NONE) · get_code("c13c8a80a222bb96")
get_data_cifar100 Not yet run danielracz/gradsim/grad_utils.py
pointer only (licence: NONE) · get_code("38ed6bea54548ead")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Feed-forward networks can be interpreted as mappings with linear decision surfaces at the level of the last layer. We investigate how the tangent space of the network can be exploited to refine the decision in case of ReLU (Rectified Linear Unit) activations. We show that a simple Riemannian metric parametrized on the parameters of the network forms a similarity function at least as good as the original network and we suggest a sparse metric to increase the similarity gap.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.13581")
get_code_for_paper("2110.13581")
have("2110.13581")

Connect an agent — have() is free.