Hyperbolicity violation conjecture for high-dimensional neural networks
Let be a mapping (neural network) as defined in the paper, with sufficiently high dimension . A hyperbolicity violation conjecture asserts that there exists at least one bifurcation chain subset . The conjecture is motivated by the expected passage through bifurcations and neutral Lyapunov directions as the network dimension and parameters vary, but the supplied text gives no resolution.
References
- D. J. Albers and J. C. Sprott, “Structural Stability and Hyperbolicity Violation in High-Dimensional Dynamical Systems”, arXiv:nlin/0408011 (2004).
Progress summary
Never refreshed
Nothing recorded yet. Refresh searches the literature and the public web for attempts on this problem, and writes the first summary here.
Solutions 0
No solutions have been posted yet.