US 12,242,947 B2
Machine learning systems with memory based parameter adaptation for learning fast and slower
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, London (GB); and Charles Blundell, London (GB)
Assigned to DeepMind Technologies Limited, London (GB)
Appl. No. 16/759,561
Filed by DeepMind Technologies Limited, London (GB)
PCT Filed Oct. 29, 2018, PCT No. PCT/EP2018/079559
§ 371(c)(1), (2) Date Apr. 27, 2020,
PCT Pub. No. WO2019/081782, PCT Pub. Date May 2, 2019.
Claims priority of provisional application 62/578,319, filed on Oct. 27, 2017.
Prior Publication US 2020/0285940 A1, Sep. 10, 2020
Int. Cl. G06N 3/045 (2023.01); G06N 3/02 (2006.01); G06N 3/04 (2023.01); G06N 3/044 (2023.01); G06N 3/084 (2023.01)
CPC G06N 3/045 (2023.01) [G06N 3/02 (2013.01); G06N 3/04 (2013.01); G06N 3/044 (2023.01); G06N 3/084 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method of processing an input data item, comprising:
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 comprising:
processing, by the first sub-model, the input data to generate a query data item;
retrieving, from an external memory storing data point-value pairs, at least one data point-value pair based upon the query data item;
modifying weights of the second sub-model using the at least one data-point value pair that was retrieved based upon the query data item without modifying weights of the first sub-model; and
processing the query data item using the second sub-model in accordance with the modified weights to generate the output data.