Machine Learning Terminology

Different Types of Neural Networks (NN)

There are several types of neural networks designed to perform specific tasks or process different kinds of data. Here are some of the most popular basic types:

• Feedforward Neural Networks (FFN)
  • The simplest type of neural network, consisting of interconnected nodes.
• Convolutional Neural Networks (CNN)
  • Primarily used for image and vision-related tasks such as object recognition.
• Reccurent Neural Networks (RRN)
  • Designed to process sequential data, like time series, by maintaining internal state variables.
• Generative Adversarial Networks (GANs)
  • GANs are used for tasks like image and music generation.

Some Definitions

The classical approach to generating a prediction is to combine scientific rules (often detailed equations) with known input to generate predicted results. This is, for example, how mathematical and finite element modeling has been performed for years. It works really well for some problems, but is completely unsuitable for other problems (e.g. handwriting recognition).

Machine Learning is a type of AI that allows software generate better predictions without being explicitly programmed using rules.

Supervised Learning (SL) is a ML approach where input values and a desired output value are used train a model.

Regression analysis is a process for estimating the relationships between dependent variables (e.g. time) and a set of independent continuous variables (e.g. stock price).