Self-organizing neural networks (SONN) driven by softmax weight renormalization are capable of finding high quality solutions of difficult assignment optimization problems. The renormalization is shaped by a temperature parameter - as the system cools down the assignment weights become increasingly crisp. It has been reported that SONN search process can exhibit complex adaptation patterns as the system cools down. Moreover, there exists a critical temperature setting at which SONN is capable of powerful intermittent search through a multitude of high quality solutions represented as meta-stable states. To shed light on such observed phenomena, we present a detailed bifurcation study of the renormalization process. As SONN cools down, new renormalization equilibria emerge in a strong structure leading to a complex skeleton of saddle type equilibria surrounding an unstable maximum entropy point, with decision enforcing "one-hot" stable equilibria. This, in synergy with the SONN input driving process, can lead to sensitivity to annealing schedules and adaptation dynamics exhibiting signatures of complex dynamical behavior. We also show that (as hypothesized in earlier studies) the intermittent search by SONN can occur only at temperatures close to the first (symmetry breaking) bifurcation temperature.
[1]
Anand Rangarajan,et al.
Self-annealing and self-annihilation: unifying deterministic annealing and relaxation labeling
,
2000,
Pattern Recognit..
[2]
Marimuthu Palaniswami,et al.
Neural techniques for combinatorial optimization with applications
,
1998,
IEEE Trans. Neural Networks.
[3]
Kate Smith-Miles,et al.
A noisy self-organizing neural network with bifurcation dynamics for combinatorial optimization
,
2004,
IEEE Transactions on Neural Networks.
[4]
Steven Gold,et al.
Softmax to Softassign: neural network algorithms for combinatorial optimization
,
1996
.
[5]
D. Canca,et al.
Manufacturing cell formation using a new self-organizing neural network
,
2002
.
[6]
Peter Tiño.
Equilibria of Iterative Softmax and Critical Temperatures for Intermittent Search in Self-Organizing Neural Networks
,
2007,
Neural Computation.
[7]
Kate Smith-Miles,et al.
Optimization via Intermittency with a Self-Organizing Neural Network
,
2005,
Neural Computation.