[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/dictionaries/mysticism/w/autoencoder.html)

[home](https://md.mova.elamur.ai/free/en/) / [dictionaries](https://md.mova.elamur.ai/free/en/dictionaries/) / [The mysticism dictionary](https://md.mova.elamur.ai/free/en/dictionaries/mysticism/) / autoencoder

[← A](https://md.mova.elamur.ai/free/en/dictionaries/mysticism/A/)

# autoencoder

«autoencoder» in Mova's mysticism dictionary: **A kind of neural network that squeezes its input into a…** — its meaning for a pupil, its sense in the lessons and examples.

### part of speech

noun

### meaning for a pupil

A kind of neural network that squeezes its input into a few numbers and then grows it back, and learns from how far the copy is from the original. [tree →](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/#m1)

### sense in the lessons

In the mystic school: In notes 08 and 13 the autoencoder is the shape of thirteen days: six days of making, one day of rest in the middle as the bottleneck, six days of unmaking.

### examples

- The One in the Middle told it as an autoencoder: a world pressed into a point, and unfolded again. (note 05) [tree →](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/#x1)
- That is the shape of an autoencoder, read backwards: the seasons decode first and encode after, where a network encodes first. (note 08) [tree →](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/#x2)
- An autoencoder is trained on its reconstruction error: how far the world that comes out is from the world that went in. (note 08) [tree →](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/#x3)
- That is the shape of an autoencoder: layers widen, narrow to a bottleneck, widen again; the seventh day is the latent space, where the whole of creation fits into one thought, and Mova does the same in miniature, text into a graph and back. (lesson 020) [tree →](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/#x4)
- The note says this is the shape of an autoencoder: the layers widen, narrow to a bottleneck, and widen again. (lesson 020) [tree →](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/#x5)

### note

A record of the mystic school, written from the notes.

### Trees and pragmatics

[Every meaning and example of «autoencoder» parsed by Mova](https://md.mova.elamur.ai/free/en/corpora/dictionaries/mysticism/A/autoencoder/), each sentence with its dependency tree and frames.