Venue
- NeurIPS 2023
Date
- 2023
Share
Towards a fuller understanding of neurons with Clustered Compositional Explanations
Biagio La Rosa*
Leilani H. Gilpin*
* External authors
NeurIPS 2023
2023
Abstract
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 used to check the alignment (i.e., the highest ones), 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 some desiderata qualities that can be used to study the explanations returned by different algorithms.
Related Publications
Recent advances in protein-protein interaction (PPI) research have harnessed the power of artificialintelligence (AI) to enhance our understanding of protein behaviour. These approaches have becomeindispensable tools in the field of biology and medicine, enabling scientists …
Non-markovian Reinforcement Learning (RL) tasks arevery hard to solve, because agents must consider the entire history ofstate-action pairs to act rationally in the environment. Most works usesymbolic formalisms (as Linear Temporal Logic or automata) to specify the temporall…
Explainable AI seeks to unveil the intricacies of black box models through post-hoc strategies or self-interpretable models. In this paper, we tackle the problem of building layers that are intrinsically explainable through logical rules. In particular, we address current st…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
