Base Classes#

This module provide basic Node class for whole brainpy.nn system.

  • brainpy.nn.Node: The fundamental class representing the node or the element.

  • brainpy.nn.RecurrentNode: The recurrent node which has a self-connection.

  • brainpy.nn.Network: The network model which is composed of multiple node elements. Once the Network instance receives a node operation, the wrapped elements, the new elements, and their connection edges will be formed as another Network instance. This means brainpy.nn.Network is only used to pack element nodes. It will be never be an element node.

  • brainpy.nn.FrozenNetwork: The whole network which can be represented as a basic elementary node when composing a larger network (TODO).

Node([name, input_shape, trainable])

Basic Node class for neural network building in BrainPy.

Network([nodes, ff_edges, fb_edges])

Basic Network class for neural network building in BrainPy.

RecurrentNode([name, input_shape, ...])

Basic class for recurrent node.

FrozenNetwork([nodes, ff_edges, fb_edges])

A FrozenNetwork is a Network that can not be linked to other nodes or networks.