# Artificial Intelligence (AI)

## Classification

* AI
  * Machine learning
    * Neural network
      * Deep learning

### Machine learning

ML algorithms leverage structured labeled data to make predictions.

Usually dataset is supervised by human at input.

Main difference with Deep Learning:

* number of layers in neural network
* whether or not human intervention is required to label data

### Neural network

* composed of node layers
* use a linear regression model - math model used to predict future events
* data is passed between nodes feed forward
* rely on training data
* NN have multiple types
  * convolutional (good for image recognition)
  * long short-term memory network (good for speach recognition)

<figure><img src="https://415484505-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LxtoAXZwwOc4XGto8vb%2Fuploads%2FBYDOzt0XLfEMwRDqpkoC%2FScreenshot%202022-11-20%20at%2020.08.31.png?alt=media&#x26;token=8166d6b8-ad32-43c4-9082-834e6b9f2c62" alt=""><figcaption></figcaption></figure>

### Deep learning

Neural network(NN) is considered a deep NN if it consists of more than three layers (including inout and out layer).

DL doesn't necessarily require a labeled dataset. It can ingest unstructured data in its raw form like text and images.

<figure><img src="https://415484505-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LxtoAXZwwOc4XGto8vb%2Fuploads%2F4zNZzfAVG1JKGZr5CRFM%2FScreenshot%202025-06-25%20at%2015.44.38.png?alt=media&#x26;token=38f47113-6575-4b7c-b18f-84909cea997a" alt=""><figcaption></figcaption></figure>
