Classify Deep Learning

1. Overview

Supervised learning is the machine learning task of learning a function that maps an input to an output based on example input-output pairs. It infers a function from labeled training data consisting of a set of training examples. In supervised learning, each example is a pair consisting of an input object (typically a vector) and the desired output value (also called the supervisory signal). A supervised learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new examples. An optimal scenario will allow for the algorithm to correctly determine the class labels for unseen instances. This requires the learning algorithm to generalize from the training data to unseen situations in a "reasonable" way (check inductive bias).

The parallel task in human and animal psychology is often referred to as concept learning.

Unsupervised learning is a type of self-organized Hebbian learning that helps find previously unknown patterns in data set without pre-existing labels. It is also known as self-organization and allows modeling probability densities of given inputs. It is one of the main three categories of machine learning, along with supervised and reinforcement learning. Semi-supervised learning has also been described and is a hybridization of supervised and unsupervised techniques.

Two of the main methods used in unsupervised learning are principal component and cluster analysis. Cluster analysis is used in unsupervised learning to group, or segment, datasets with shared attributes in order to extrapolate algorithmic relationships. Cluster analysis is a branch of machine learning that groups the data that has not been labelled, classified or categorized. Instead of responding to feedback, cluster analysis identifies commonalities in the data and reacts based on the presence or absence of such commonalities in each new piece of data. This approach helps detect anomalous data points that do not fit into either group.

A central application of unsupervised learning is in the field of density estimation in statistics, though unsupervised learning encompasses many other domains involving summarizing and explaining data features. It could be contrasted with supervised learning by saying that whereas supervised learning intends to infer a conditional probability distribution $p_{X}=(x\: |\: y)$ conditioned on the label $y$ of input data; unsupervised learning intends to infer an a priori probability distribution $p_{X}=(x)$ Generative adversarial networks can also be used with unsupervised learning, though they can also be applied to supervised and reinforcement techniques.

2. Description

3. References

https://en.wikipedia.org/wiki/Supervised_learning

https://en.wikipedia.org/wiki/Unsupervised_learning