5 citations · 12 across the 5 of their papers we have counts for
5 papers
Diversity and Adaptation in Large Population Games
K. Y. Michael Wong, S. W. Lim, Peixun Luo
We consider a version of large population games whose players compete for resources using strategies with adaptable preferences. The system efficiency is measured by the variance o…
Dynamical and Stationary Properties of On-line Learning from Finite Training Sets
Peixun Luo, K. Y. Michael Wong
The dynamical and stationary properties of on-line learning from finite training sets are analysed using the cavity method. For large input dimensions, we derive equations for the…
The Cavity Approach to Noisy Learning in Nonlinear Perceptrons
Peixun Luo, K. Y. Michael Wong
We analyze the learning of noisy teacher-generated examples by nonlinear and differentiable student perceptrons using the cavity method. The generic activation of an example is a f…
Mean-field theory of learning: from dynamics to statics
K. Y. Michael Wong, S. Li, Peixun Luo
Using the cavity method and diagrammatic methods, we model the dynamics of batch learning of restricted sets of examples. Simulations of the Green's function and the cavity activat…
Sacrificial Learning in Nonlinear Perceptrons
Peixun Luo, K. Y. Michael Wong
Using the cavity method we consider the learning of noisy teacher-generated examples by a nonlinear student perceptron. For insufficient examples and weak weight decay, the activat…