ตัวเข้ารหัส คอขวด และตัวถอดรหัส

An autoencoder learns to copy its input to its output. The trick is forcing the data through a tiny middle, so it must learn what truly matters.

The encoder takes your input and squeezes it down into a small set of numbers. Think of it as packing a suitcase: only the essentials fit.

The bottleneck is the smallest layer in the middle. Its tiny size is the whole point: the network cannot just memorize, it has to summarize. 🎯

The compressed numbers in the bottleneck form the latent code. This short vector is a dense, learned summary of your original input.

The decoder takes the latent code and tries to rebuild the full original input. It unpacks the suitcase back into something useful.

You measure success with reconstruction loss: how close the output is to the input. Lower loss means a better rebuild.

An encoder is often just stacked linear layers shrinking the size. Here input 784 becomes a latent code of just 32 numbers.

The decoder usually mirrors the encoder, growing the code back to full size. Symmetry keeps the design simple and balanced.

If the middle were large, the net could just copy values straight through. The narrow bottleneck forces it to find real structure in the data.

Autoencoders learn from data alone, no labels needed. This makes them a classic example of unsupervised learning. ✨

All possible latent codes together form the latent space. Similar inputs land near each other, giving you a compact, meaningful map of your data.

Let us check the core idea of the bottleneck.

You met the three parts: an encoder that compresses, a tiny bottleneck holding the latent code, and a decoder that rebuilds. Reconstruction loss guides it all. 🎉