Lwpr Class Reference
#include <lwpr.h>
List of all members.
Detailed Description
LWPR is a regresion technique mainly developed by Sethu Vijayakumar. This file tests an implementation of this algorithm, coded by Narayanan Edakunni and Giorgos Petkos, cleaned up and made more efficient by myself.
When using this code, please cite
Sethu Vijayakumar, Aaron D'Souza and Stefan Schaal, "Incremental Online Learning in High Dimensions", Neural Computation, 17:12, pp. 2602-2632 (2005)
- Examples:
-
tests/main.cpp.
Definition at line 161 of file lwpr.h.
Public Member Functions
-
Lwpr ()
- Constructor, takes parameters from parameter file.
-
void learn (const doubleA &X, const doubleA &Y)
- updates the LWPR model given a new datapoint x->y, or a batch of data
-
void map (const doubleA &X, doubleA &Y)
- predicts the output Y for a given input X -- also for batch data
-
void updaterfs (const doubleA &X, const doubleA &Y)
- same as learn(X,Y) - for compatibility reasons
-
doubleA predict (const doubleA &x)
- same { doubleA y; map(x,y); return y; } - for compatibility reasons
-
void useNormalization (const doubleA &mean, const doubleA &trans)
- tells LWPR to use a specific normalization for inputs (during both, learn and map): the mean is subtracted, the trans multiplied (trans can be 0-, 1-, or 2-dimensional for scalar, vector-element-wise and matrix multiplications, respectively)
-
void learnNormalization (doubleA &X)
- uses a normalization learned from the given batch of input data: the i-th component of an input vector will be multiplied by 1./standard-deviation(i-th dimension)
-
void save (char *)
- saves the LWPR model in the file given as parameter
-
void load (char *, bool alsoParameters=true)
- loads the LWPR model from the file given as parameter
-
double confidence (const doubleA &x)
- get the confidence bounds (standard deviation) at some input point
-
void report (std::ostream &os)
- preliminary -- output useful readable state information
-
int get_rfs_no (int out_dim)
- get the number of rfs for the given output dimension
-
double get_proj_average (int out_dim)
- average number of projection dimensions used in the local models
Public Attributes
The documentation for this class was generated from the following file:
[]