September 2016
Beginner to intermediate
344 pages
7h 44m
English
A multilayer perceptron classifier (MLPC) is a feedforward artificial neural network with multiple layers of nodes connected to each other in a directed fashion. It uses a supervised learning technique called backpropagation for training the network.
Nodes in the intermediary layer use the sigmoid function to restrict the output between 0 and 1, and the nodes in the output layer use the softmax function, which is a generalized version of the sigmoid function.
Scala:
scala> import org.apache.spark.ml.classification.MultilayerPerceptronClassifier import org.apache.spark.ml.classification.MultilayerPerceptronClassifier scala> import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator import org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator ...
Read now
Unlock full access