SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.05149 · 2021

Logic Explained Networks

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 0 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
pietrobarbiero/logic_explainer_networks canonical 0 of 7
FunctionStatusWhere it lives
accuracy_score Not yet run pietrobarbiero/logic_explainer_networks/lens/logic/metrics.py
code served (permissive licence) · get_code("2fc1ba2f197007cf")
compute_fol_formula Not yet run pietrobarbiero/logic_explainer_networks/lens/logic/psi_nn.py
code served (permissive licence) · get_code("6cf788a92c890917")
explain_global Not yet run pietrobarbiero/logic_explainer_networks/lens/logic/explain.py
code served (permissive licence) · get_code("ab121c4402f079e3")
explain_local Not yet run pietrobarbiero/logic_explainer_networks/lens/logic/explain.py
code served (permissive licence) · get_code("b88b7add4f88494c")
fidelity Not yet run pietrobarbiero/logic_explainer_networks/lens/logic/metrics.py
code served (permissive licence) · get_code("cb7e38e73fd7d506")
generate_fol_explanations Not yet run pietrobarbiero/logic_explainer_networks/lens/logic/psi_nn.py
code served (permissive licence) · get_code("11ca4af975545fff")
generate_fol_explanations_from_data Not yet run pietrobarbiero/logic_explainer_networks/lens/logic/psi_nn.py
code served (permissive licence) · get_code("7a46ca136a2edbac")

Repositories linked to this paper

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

Abstract

The large and still increasing popularity of deep learning clashes with a major limit of neural network architectures, that consists in their lack of capability in providing human-understandable motivations of their decisions. In situations in which the machine is expected to support the decision of human experts, providing a comprehensible explanation is a feature of crucial importance. The language used to communicate the explanations must be formal enough to be implementable in a machine and friendly enough to be understandable by a wide audience. In this paper, we propose a general approach to Explainable Artificial Intelligence in the case of neural architectures, showing how a mindful design of the networks leads to a family of interpretable deep learning models called Logic Explained Networks (LENs). LENs only require their inputs to be human-understandable predicates, and they provide explanations in terms of simple First-Order Logic (FOL) formulas involving such predicates. LENs are general enough to cover a large number of scenarios. Amongst them, we consider the case in which LENs are directly used as special classifiers with the capability of being explainable, or when they act as additional networks with the role of creating the conditions for making a black-box classifier explainable by FOL formulas. Despite supervised learning problems are mostly emphasized, we also show that LENs can learn and provide explanations in unsupervised learning settings. Experimental results on several datasets and tasks show that LENs may yield better classifications than established white-box models, such as decision trees and Bayesian rule lists, while providing more compact and meaningful explanations.

For agents

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

get_harvested_code_for_paper("2108.05149")
get_code_for_paper("2108.05149")
have("2108.05149")

Connect an agent — have() is free.