# Deep Learning

## Deep Learning vs Machine Learning

Deep Learning is a subtype of Machine Learning focus on Images as data.

Machine Learning | Deep Learning | |
---|---|---|

How does it work? | Use types of automated algrithms which learn to predict future decisions and model function using the data fed to it. | Interprets data features and its relationships using neural networks which pass the relevant information through several stages of data processing. |

Management | The various algorithms are directed by the analysis to examine the different variables in the dataset | Once they are implemented, the algorithms are usually self-directed for the relevant data analysis |

Number of Data Points | Usually, there are a gew thousand data points used for the analysis. | There a few million data points used for the analysis. |

Output | The output is usually a numerical value, like a score or a classification | The output can be anything from a score, an element, free text or sound, etc. |

## Deep Learning Types

## Deep Learning Models/Algorithms

There is a different models or approach those define algorithms based on mathematics, statistics and matrix models in deep learning.

### Unsupervised Pretrained Networks

See main article UPN.

### Convolutional Neural Networks

Is the model based on ANN to solve complex problems which depends of data extracted from images.

See main article CNN.