LioNets: Local Interpretation of Neural Networks through Penultimate Layer Decoding
This work addresses the need for more accurate and reliable explainable AI methods in applications like smart homes and healthcare, though it appears incremental by focusing on a specific improvement in neighborhood generation.
The paper tackles the problem of generating local explanations for neural network decisions by creating a neighborhood generation process that ensures adjacency between generated neighbors and the instance, leveraging the network's architecture.
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.