Deep learning

Neural networks with many successive layers and training methods tuned to stacked representations (often rebranded circa 2006–2012 revival).

Deep learning usually means networks with multiple hidden layers: or very wide modern Transformers: to learn hierarchical feature representations from raw-ish inputs such as pixels, waveforms, and tokens.

Breakthrough eras include CNNs on perception and attention-based Transformers, including large language models (LLMs), pretrained on enormous corpora.