abstract class NeuralNet extends Predictor with Error
The NeuralNet abstract class provides the basic structure and API for
a variety of Neural Networks.
- Alphabetic
- By Inheritance
- NeuralNet
- Error
- Predictor
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
-
new
NeuralNet(x: MatriD, y: MatriD, eta: Double = 0.1)
- x
the m-by-nx input matrix (training data consisting of m input vectors)
- y
the m-by-ny output matrix (training data consisting of m output vectors)
- eta
the learning/convergence rate (typically less than 1.0)
Abstract Value Members
-
abstract
def
crossVal(k: Int = 10): Unit
The 'crossVal' abstract method must be coded in implementing classes to call the above 'crossValidate' method.
The 'crossVal' abstract method must be coded in implementing classes to call the above 'crossValidate' method. The 'algor' parameter may be specified as a lambda function to create the prediction algorithm.
- k
the number of crosses and cross-validations (defaults to 10x).
-
abstract
def
predict(z: MatriD): MatriD
Given a new input matrix 'z', predict the output/response matrix 'f(z)'.
Given a new input matrix 'z', predict the output/response matrix 'f(z)'.
- z
the new input matrix
-
abstract
def
predictV(z: VectoD): VectoD
Given a new input vector 'z', predict the output/response vector 'f(z)'.
Given a new input vector 'z', predict the output/response vector 'f(z)'.
- z
the new input vector
-
abstract
def
setWeights(stream: Int = 0, limit: Double = 1.0 / sqrt (nx)): Unit
Set the initial weight matrix (ces) with values in (0, limit) before training.
Set the initial weight matrix (ces) with values in (0, limit) before training.
- stream
the random number stream to use
- limit
the maximum value for any weight
-
abstract
def
train(): NeuralNet
Given training data 'x' and 'y', fit the parameter/weight matrix.
-
abstract
def
weights: Array[MatriD]
Return the weight matrix.
Concrete Value Members
-
def
coefficient: VectoD
Return the vector of coefficient/parameter values.
Return the vector of coefficient/parameter values.
- Definition Classes
- Predictor
- def crossValidate(algor: (MatriD, MatriD) ⇒ NeuralNet, k: Int = 10): Array[Statistic]
-
def
eval(xx: MatriD, yy: MatriD): Unit
Evaluate the quality of the fit for the parameter/weight matrices on the test dataset.
Evaluate the quality of the fit for the parameter/weight matrices on the test dataset.
- xx
the test input data matrix
- yy
the test output response matrix
-
def
eval(): Unit
Evaluate the quality of the fit for the parameter weight matrices on the the entire dataset or the training dataset.
-
def
eval(xx: MatriD, yy: VectoD): Unit
Compute the error and useful diagnostics for the test dataset.
Compute the error and useful diagnostics for the test dataset.
- xx
the test data matrix
- yy
the test response vector FIX - implement in classes
- Definition Classes
- Predictor
-
def
fitLabel: Seq[String]
Return the labels for the quality of fit measures.
-
def
fitMap(): Unit
Show 'fitMap' for each y-column.
-
final
def
flaw(method: String, message: String): Unit
- Definition Classes
- Error
-
def
predict(z: VectoD): Double
Given a new input vector 'z', predict the output/response value 'f(z)'.
-
def
predict(z: VectoI): Double
Given a new discrete data vector z, predict the y-value of f(z).
Given a new discrete data vector z, predict the y-value of f(z).
- z
the vector to use for prediction
- Definition Classes
- Predictor
-
def
reset(eta_: Double): Unit
Reset the learning rate 'eta'.
Reset the learning rate 'eta'.
- eta_
the learning rate
-
def
residual: VectoD
Return the vector of residuals/errors.
Return the vector of residuals/errors.
- Definition Classes
- Predictor
-
def
train(yy: VectoD): NeuralNet
Given training data 'x' and 'yy', fit the parameter/weight matrix.