Home » Publication » 28257

Dettaglio pubblicazione

2023, Advances in neural Information processing systems, Pages 70333-70354 (volume: 36)

Towards a fuller understanding of neurons with Clustered Compositional Explanations (04b Atto di convegno in volume)

LA ROSA Biagio, Gilpin Leilani H., Capobianco Roberto

Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations (i.e., the highest ones) used to check the alignment, thus lacking completeness. In this paper, we propose a generalization, called Clustered Compositional Explanations, that combines Compositional Explanations with clustering and a novel search heuristic to approximate a broader spectrum of the neuron behavior. We define and address the problems connected to the application of these methods to multiple ranges of activations, analyze the insights retrievable by using our algorithm, and propose desiderata qualities that can be used to study the explanations returned by different algorithms.
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma