Paragraph 81

Paragraph 81

Application: PER-17

Matter Number PER-17
Paragraph Number 81
Application Number
Reference Case 1 PER-17
Reference Case 2
Created 1/6/24, 10:05 PM
Modified 1/6/24, 10:05 PM
Id 15,487
Content
With reinforcement learning, input and output pairs can never be presented; reinforcement learning can map a state, e.g. a clinical state of a patient, and can develop predictions, actions or treatment the system can make. With representation learning algorithms input information can be preserved but transformed to make it more useful, e.g. as a pre-processing step, prior to performing classification or predictions, allowing reconstruction of the inputs coming from the unknown data generating distribution.
Notes Added by DJM Jan 2024