Machine learning systems with memory based parameter adaptation for learning fast and slower

US12242947B2 · kind B2 · utility

Assignee

• DeepMind Technologies Limited · GB

Inventors

• Pablo Sprechmann · London, GB
• Siddhant Jayakumar · London, GB
• Jack William Rae · London, GB
• Alexander Pritzel · London, GB
• Adrià Puigdomènech Badia · London, GB
• Oriol Vinyals · London, GB
• Razvan Pascanu · Letchworth, GB
• Charles Blundell · London, GB

Key dates

• Filing date: Oct 29, 2018
• Grant date: Mar 4, 2025
• Expiry date: Jan 28, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/092
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

There is described herein a computer-implemented method of processing an input data item. The method comprises processing the input data item using a parametric model to generate output data, wherein the parametric model comprises a first sub-model and a second sub-model. The processing comprises processing, by the first sub-model, the input data to generate a query data item, retrieving, from a memory storing data point-value pairs, at least one data point-value pair based upon the query data item and modifying weights of the second sub-model based upon the retrieved at least one data point-value pair. The output data is then generated based upon the modified second sub-model.