# LioNets: Local Interpretation of Neural Networks through Penultimate Layer Decoding

## TL;DR

This paper introduces LioNets, a local explanation method for neural networks that ensures the generated neighbors are truly adjacent to the instance by considering the network's architecture during neighborhood creation.

## Contribution

LioNets is a novel approach that improves local interpretability of neural networks by architecture-aware neighborhood generation for explanations.

## Key findings

- Ensures true adjacency between neighbors and instances.
- Provides more faithful local explanations for neural networks.
- Outperforms agnostic methods in local interpretability.

## Abstract

Technological breakthroughs on smart homes, self-driving cars, health care and robotic assistants, in addition to reinforced law regulations, have critically influenced academic research on explainable machine learning. A sufficient number of researchers have implemented ways to explain indifferently any black box model for classification tasks. A drawback of building agnostic explanators is that the neighbourhood generation process is universal and consequently does not guarantee true adjacency between the generated neighbours and the instance. This paper explores a methodology on providing explanations for a neural network's decisions, in a local scope, through a process that actively takes into consideration the neural network's architecture on creating an instance's neighbourhood, that assures the adjacency among the generated neighbours and the instance.