|US 9,811,585 B2|
|Minna Hellstrom, Tuusula (FI); Mikko Lonnfors, Helsinki (FI); Eki Monni, Espoo (FI); Istvan Beszteri, Espoo (FI); Mikko Terho, Tampere (FI); and Leo Karkkainen, Helsinki (FI)|
|Assigned to Nokia Technologies Oy, Espoo (FI)|
|Appl. No. 14/379,574
|Filed by Minna Hellstrom, Tuusula (FI); Mikko Lonnfors, Helsinki (FI); Eki Monni, Espoo (FI); Istvan Beszteri, Espoo (FI); Mikko Terho, Tampere (FI); and Leo Karkkainen, Helsinki (FI)|
|PCT Filed Feb. 22, 2012, PCT No. PCT/FI2012/050179
§ 371(c)(1), (2), (4) Date Dec. 1, 2014,
PCT Pub. No. WO2013/124520, PCT Pub. Date Aug. 29, 2013.
|Prior Publication US 2015/0178378 A1, Jun. 25, 2015|
|Int. Cl. G06F 15/18 (2006.01); G06F 17/30 (2006.01); G06Q 10/10 (2012.01); G06N 5/00 (2006.01); G06Q 10/04 (2012.01)|
|CPC G06F 17/30663 (2013.01) [G06F 17/30867 (2013.01); G06N 5/003 (2013.01); G06Q 10/04 (2013.01); G06Q 10/10 (2013.01)]||20 Claims|
|1. A method, comprising:
causing at least a part of a first experience matrix and at least a part of at least a second experience matrix to be combined to obtain a combined experience matrix, said experience matrices comprising sparse vectors, and said experience matrices comprising information of at least one system,
accessing at least a part of at least one sparse vector of said combined experience matrix to form a prediction output,
controlling a system in response to said prediction output; and
forming an incremental experience matrix corresponding to another experience matrix, said incremental experience matrix comprising data of at least one system or apparatus with said data being related to a context that is restricted in terms of time or topic.