Period-halving Bifurcation of a Neuronal Recurrence Equation

We study the sequences generated by neuronal recurrence equations of the form $x(n) = {\bf 1}[\sum_{j=1}^{h} a_{j} x(n-j)- \theta]$. From a neuronal recurrence equation of memory size $h$ which describes a cycle of length $\rho(m) \times lcm(p_0, p_1,..., p_{-1+\rho(m)})$, we construct a set of $\rho(m)$ neuronal recurrence equations whose dynamics describe respectively the transient of length $O(\rho(m) \times lcm(p_0, ..., p_{d}))$ and the cycle of length $O(\rho(m) \times lcm(p_{d+1}, ..., p_{-1+\rho(m)}))$ if $0 \leq d \leq -2+\rho(m)$ and 1 if $d=\rho(m)-1$. This result shows the exponential time of the convergence of neuronal recurrence equation to fixed points and the existence of the period-halving bifurcation.

Réseaux d'Automates de Caianiello Revisité

We exhibit a family of neural networks of McCulloch and Pitts of size $2nk+2$ which can be simulated by a neural networks of Caianiello of size $2n+2$ and memory length $k$. This simulation allows us to find again one of the result of the following article: [Cycles exponentiels des r\'{e}seaux de Caianiello et compteurs en arithm\'{e}tique redondante, Technique et Science Informatiques Vol. 19, pages 985-1008] on the existence of neural networks of Caianiello of size $2n+2$ and memory length $k$ which describes a cycle of length $k \times 2^{nk}$.