Supervised Learning
In Supervised Learning, a teacher teacher provides a category level or cost for each pattern in a training set, and seeks to reduce the sum of the cost for these patterns.
How can we be sure that a particular learning algorithm is powerful enough to learn the solution to a given problem and that it will be stable to parameter variations ? how can we determine if it will converge infinite time or if it will scale reasonably with the number of training patterns, the number of input features or the number of categories ? How can we ensure that the learning algorithm appropriately favours "simple" solutions (fig 2) rather than complicated ones (fig 1).
Unsupervised Learning
In unsupervised learning for clustering there is no explicit teacher and the system forms "clusters" or "natural groupings" of the input patterns. "Natural" is always define explicitly or implicitly in the clustering system itself and given a particular set of patterns for cost function, different clustering algorithms lead to different clusters. open the user will set the hypothesis number of different clusters ahead of time, but how should this be done? How do we avoid inappropriate representations?
To solve this problem there are many algorithms like k mean clustering.
Post a Comment