Seeing and squeezingLesson 3 of 9
Squeeze it through a bottleneck
An autoencoder must rebuild 16 pixels from two numbers. The cross motif rebuilds perfectly; an all-dark tin loses half its pixels.
Locked
Unlock the rest of Deep Learning: from one neuron to a transformer.
- Every lesson, every resource, unlocked instantly.
- Track progress and pick up where you left off.
- Free preview lessons stay readable from the outline.