Skip to content

Files

Latest commit

 

History

History
27 lines (17 loc) · 1.08 KB

ctrnn.rst

File metadata and controls

27 lines (17 loc) · 1.08 KB

Continuous-time recurrent neural network implementation

.. index:: ! continuous-time

.. index:: recurrent

.. index:: ! ctrnn

The default :term:`continuous-time` :term:`recurrent` neural network (CTRNN) :py:mod:`implementation <ctrnn>` in neat-python is modeled as a system of ordinary differential equations, with neuron potentials as the dependent variables.

\tau_i \frac{d y_i}{dt} = -y_i + f_i\left(\beta_i + \sum\limits_{j \in A_i} w_{ij} y_j\right)

Where:

The time evolution of the network is computed using the forward Euler method:

y_i(t+\Delta t) = y_i(t) + \Delta t \frac{d y_i}{dt}