When considering the representation of data, we come across learning algorithms.

<aside> 💡

A "learning algorithm" in a neural network is the computational process that allows the network to adjust its internal parameters, like the weights between neurons, based on the data it is exposed to, enabling it to learn patterns and improve its predictions over time

</aside>

An example of one would the autoencoder . When considering encoders we have an encoder that converts input data into a different representation and a decoder that converts the new representation back into the original format.

When considering the human mind, we are faced with a wide variety of data. Thus it is helpful for us to have concepts or abstractions that help us make sense of the data.