Related Experiment Videos
Global asymptotic stability of neural networks with discontinuous activations
Jiafu Wang1, Lihong Huang, Zhenyuan Guo
1College of Mathematics and Econometrics, Hunan University, Changsha, Hunan, PR China. jfwangmath@163.com
Abstract:
Without assuming the boundedness and monotonicity of the neuron activations, we discuss the dynamics of a class of neural networks with discontinuous activation functions. The Leray-Schauder theorem of set-valued maps is successfully employed to derive the existence of an equilibrium point. A Lyapunov-like approach is applied to differential equations with discontinuous right-hand sides modeling the neural network dynamics, which yields conditions for global convergence or convergence in finite time. The obtained results extend previous works on global stability of neural networks with continuous neuron activations or discontinuous neuron activations.
Related Concept Videos
Limits with Oscillating Discontinuities
BIBO stability of continuous and discrete -time systems
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system.
Neural Regulation
Stability of structures
Improper Integrals: Discontinuous Integrands
Continuity for Functions of Multiple Variables