Towards a fuller understanding of neurons with Clustered Compositional Explanations

Biagio La Rosa · Leilani Gilpin · Roberto Capobianco

Great Hall & Hall B1+B2 (level 1) #1522
[ ] [ Project Page ]
Tue 12 Dec 8:45 a.m. PST — 10:45 a.m. PST


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.

Chat is not available.