Home | Trees | Indices | Help |
|
---|
|
Learn the topological structure of the input data by building a corresponding graph approximation. The algorithm expands on the original Neural Gas algorithm (see mdp.nodes NeuralGasNode) in that the algorithm adds new nodes are added to the graph as more data becomes available. Im this way, if the growth rate is appropriate, one can avoid overfitting or underfitting the data. More information about the Growing Neural Gas algorithm can be found in B. Fritzke, A Growing Neural Gas Network Learns Topologies, in G. Tesauro, D. S. Touretzky, and T. K. Leen (editors), Advances in Neural Information Processing Systems 7, pages 625-632. MIT Press, Cambridge MA, 1995. **Attributes and methods of interest** - graph -- The corresponding `mdp.graph.Graph` object
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
Inherited from Inherited from |
|||
Inherited from Node | |||
---|---|---|---|
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|||
|
|
|||
Inherited from Node | |||
---|---|---|---|
|
|||
|
|
|||
Inherited from |
|||
Inherited from Node | |||
---|---|---|---|
_train_seq List of tuples:: |
|||
dtype dtype |
|||
input_dim Input dimensions |
|||
output_dim Output dimensions |
|||
supported_dtypes Supported dtypes |
|
Growing Neural Gas algorithm. :Parameters: start_poss sequence of two arrays containing the position of the first two nodes in the GNG graph. If unspecified, the initial nodes are chosen with a random position generated from a gaussian distribution with zero mean and unit variance. eps_b coefficient of movement of the nearest node to a new data point. Typical values are 0 < eps_b << 1 . Default: 0.2 eps_n coefficient of movement of the neighbours of the nearest node to a new data point. Typical values are 0 < eps_n << eps_b . Default: 0.006 max_age remove an edge after `max_age` updates. Typical values are 10 < max_age < lambda. Default: 50 `lambda_` insert a new node after `lambda_` steps. Typical values are O(100). Default: 100 alpha when a new node is inserted, multiply the error of the nodes from which it generated by 0<alpha<1. A typical value is 0.5. Default: 0.5 d each step the error of the nodes are multiplied by 0<d<1. Typical values are close to 1. Default: 0.995 max_nodes maximal number of nodes in the graph. Default: 2^31 - 1
|
|
|
Return the two nodes in the graph that are nearest to x and their squared distances. (Return ([node1, node2], [dist1, dist2]) |
Insert a new node in the graph where it is more necessary (i.e. where the error is the largest). |
Move a node by eps in the direction x. |
Remove all edges older than the maximal age. |
|
|
|
Assign each point in the input data to the nearest node in the graph. Return the list of the nearest node instances, and the list of distances. Executing this function will close the training phase if necessary. |
Update the internal structures according to the input data `x`. `x` is a matrix having different variables on different columns and observations on the rows. By default, subclasses should overwrite `_train` to implement their training phase. The docstring of the `_train` method overwrites this docstring. Note: a subclass supporting multiple training phases should implement the *same* signature for all the training phases and document the meaning of the arguments in the `_train` method doc-string. Having consistent signatures is a requirement to use the node in a flow.
|
Home | Trees | Indices | Help |
|
---|
Generated by Epydoc 3.0.1 on Thu Mar 10 15:28:15 2016 | http://epydoc.sourceforge.net |