class
NNetClassifier[L, T] extends Classifier[L, T]
Instance Constructors
-
new
NNetClassifier(nnet: NeuralNetwork, inputEncoder: (T) ⇒ DenseVector[Double], labelIndex: Index[L])
Value Members
-
final
def
!=(arg0: AnyRef): Boolean
-
final
def
!=(arg0: Any): Boolean
-
final
def
##(): Int
-
final
def
==(arg0: AnyRef): Boolean
-
final
def
==(arg0: Any): Boolean
-
def
andThen[A](g: (L) ⇒ A): (T) ⇒ A
-
def
apply(o: T): L
-
final
def
asInstanceOf[T0]: T0
-
def
classify(o: T): L
-
def
clone(): AnyRef
-
def
compose[A](g: (A) ⇒ T): (A) ⇒ L
-
final
def
eq(arg0: AnyRef): Boolean
-
def
equals(arg0: Any): Boolean
-
def
finalize(): Unit
-
final
def
getClass(): Class[_]
-
def
hashCode(): Int
-
final
def
isInstanceOf[T0]: Boolean
-
def
map[M](f: (L) ⇒ M): Classifier[M, T]
-
final
def
ne(arg0: AnyRef): Boolean
-
final
def
notify(): Unit
-
final
def
notifyAll(): Unit
-
def
scores(o: T): Counter[L, Double]
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
-
def
toString(): String
-
final
def
wait(): Unit
-
final
def
wait(arg0: Long, arg1: Int): Unit
-
final
def
wait(arg0: Long): Unit
Inherited from (T) ⇒ L
Inherited from AnyRef
Inherited from Any
A NeuralNetwork classifier uses a neural network to get unnormalize log probabilities for the scores of the classifier. These are used to predict terms.