Axiomatic Scalable Neurocontroller Analysis via the Shapley Value

  title={Axiomatic Scalable Neurocontroller Analysis via the Shapley Value},
  author={Alon Keinan and Ben Sandbank and Claus C. Hilgetag and Isaac Meilijson and Eytan Ruppin},
  journal={Artificial Life},
One of the major challenges in the field of neurally driven evolved autonomous agents is deciphering the neural mechanisms underlying their behavior. Aiming at this goal, we have developed the multi-perturbation Shapley value analysis (MSA)the first axiomatic and rigorous method for deducing causal function localization from multiple-perturbation data, substantially improving on earlier approaches. Based on fundamental concepts from game theory, the MSA provides a formal way of defining and… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 27 extracted citations

Smart Health

Lecture Notes in Computer Science • 2015
View 10 Excerpts
Highly Influenced

Analysing Neural Network Topologies : a Game Theoretic Approach

Julian Stiera, Gabriele Gianinib, Michael Granitzera, Konstantin Zieglera
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 37 references

Multi-knockout genetic network analysis: the Rad6 example

Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004. • 2004
View 2 Excerpts

Controlled analysis of neurocontrollers with informational lesioning.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences • 2003
View 5 Excerpts

Similar Papers

Loading similar papers…