Distinguish between Supervised and Un-supervised learning

46views

written 7.4 years ago by

Supervised learning	Un-supervised learning
Supervised learning where neural is provided with a data set consisting with input vector and target output vector associated with each input vector. This data set referred to as raining set.	Un-supervised learning where neural is provided with a data set consisting with input vector with no assistance from the output sources.
The aim of supervised training is then to adjust the weight values such that the error between the real output, o=f(net- θ) of neural network and the target output t is minimized	The aim of un-supervised learning is to discovers pattern or features in the input data with no assistance from the output sources.
Supervised learning algorithm basically perform the classification and recognition of the patterns.	Un-supervised learning algorithm basically perform the clustering of the training patterns.
NN model of supervised learning is Perceptron and Feed-forward NN	NN model of supervised learning is Self-Organizing Maps

The causal structure of (a) supervised and (b) unsupervised learning. In supervised learning, one set of observations, called inputs, is assumed to be the cause of another set of observations, called outputs, while in unsupervised learning all observations are assumed to be caused by a set of latent variables.

enter image description here

ADD COMMENT EDIT