Optimizing neural network topology using Shapley value
Florin Leon · 2014
The paper proposes a destructive method for optimizing the topology of neural networks based on the Shapley value, a game theoretic solution concept which estimates the contribution of each network element to the overall performance. More network elements can be simultaneously pruned, which can lead to shorter execution times and better results. An evolutionary hill climbing procedure is used to fine-tune the network after each simplification.