For the CVNN defined by (1), assume that the network parameters and the activation function satisfy assumptions ((mathbf{H1})) and ((mathbf{H2})), respectively.
For the CVNNs defined by (2), assume that the network parameters and the activation function satisfy conditions ((mathbf{H}_{1})), ((mathbf{H}_{2})) and ((mathbf{H}_{3})).
Since they play the role of activation functions, parameters ρ syn and ϕ σ are assumed to be sufficiently large.
So, the crisis of parameter uncertainties, including errors, stochastic disturbance, leakage delays, distributed delays, and the activation function of the addressed GRNs, is identified by sector-bounded nonlinearities.
and f is the activation function and can be a sigmoid function or tanh function.
The neural network under study involves parameter uncertainties, stochastic disturbances and time-varying delays, and the activation functions are characterized by sector-like nonlinearities.
The network structures and the parameters of the activation function are important factors when developing neural network models.
The activation function has two tunable parameters, which give more flexibility to design the neural networks.
NM signals orchestrate both adjustments in activation function and synaptic input, with NM activation often depressing synapses, but increasing the variability in the activation function through selected conductance changes (activating k-parameters).
The steepness of the activation function is determined by the parameter h.
A specific learning algorithm, based on the adaptation of local parameters of the activation function, is derived.
