Learning methods

Introduced: January 2000

Full Title

Computing arrangements based on biological models > Neural networks > Learning methods

IPC and CPC are identically structured here. All 12 subcodes exist in both systems.

IPC defines codes here since 2023.

Navigate with arrow keys, Enter to open

G06N 3/082 modifying the architecture, e.g. adding, deleting or silencing nodes or connections since 2023 IPC+CPC Available in IPC and CPC
G06N 3/084 Backpropagation, e.g. using gradient descent since 2023 IPC+CPC Available in IPC and CPC
G06N 3/086 using evolutionary algorithms, e.g. genetic algorithms or genetic programming since 2023 IPC+CPC Available in IPC and CPC
G06N 3/088 Non-supervised learning, e.g. competitive learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/0895 Weakly supervised learning, e.g. semi-supervised or self-supervised learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/09 Supervised learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/091 Active learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/092 Reinforcement learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/094 Adversarial learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/096 Transfer learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/098 Distributed learning, e.g. federated learning since 2023 IPC+CPC Available in IPC and CPC
G06N 3/0985 Hyperparameter optimisation; Meta-learning; Learning-to-learn since 2023 IPC+CPC Available in IPC and CPC

Class G06,2013–2023, worldwide · Source: EPO PATSTAT

Class G06,2013–2023, worldwide · Source: EPO PATSTAT