Updating learned models
Methods and systems are disclosed for updating learned models. An embodiment comprises receiving a plurality of data sets representing sensed data from one or more devices and determining, using one or more local learned models, local parameters based on the received data sets. Another operation may comprise generating a combined data set by combining the plurality of data sets and, determining, using one or more local learned models, global parameters based on the combined data set. Another operation may comprise transmitting, to a remote system, the global parameters for determining updated global parameters using one or more global learned models based at least partially on the global parameters, and receiving, from the remote system, the updated global parameters. Another operation may comprise updating the one or more local learned models using both the local parameters and updated global parameters.
1. An apparatus comprising:
at least one processor; and
at least one memory including computer code,
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform:
receiving, via a local network, a plurality of data sets representing sensed data from one or more devices;
determining, using one or more local learned models, local parameters based on the received data sets;
generating a combined data set by combining the plurality of data sets;
determining, using the one or more local learned models, global parameters based on the combined data set;
causing transmittal of, to a remote system, remote from the apparatus, and via a different network than the local network via which the plurality of the data sets are received, the global parameters for determining updated global parameters using one or more global learned models based at least partially on the global parameters;
receiving, from the remote system, the updated global parameters; and
updating the one or more local learned models using both the local parameters and updated global parameters.
2. The apparatus as claimed in claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to perform to:
transmitting, to the one or more devices, the updated one or more local learned models.
3. The apparatus as claimed in claim 1 , wherein the one or more devices are members of a predetermined group of devices.
4. The apparatus as claimed in claim 1 , wherein the at least one memory and the computer program code and further configured to, with the at least one processor, cause the apparatus at least to perform:
identifying from which device each of the plurality of data sets is received from such that the generated local parameters are particular to each of the identified devices.
5. The apparatus as claimed claim 1 , wherein at least one of the received data sets comprises at least one missing data field, and wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to perform:
inferring and inserting the at least one missing data field using the one or more local learned models.
6. The apparatus a claimed in claim 1 , wherein the at least one memory and the computer program code and further configured to, with at the least one processor, cause the apparatus at least to perform:
normalizing the plurality of data sets; and/or
using the plurality of data sets to capture high-order correlations.
7. The apparatus as claimed in claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to perform:
combining the local parameters and the updated global parameters; and
updating the one or more local learned models using the combined parameters.
8. The apparatus as claimed in claim 1 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus at least to perform:
combining the plurality of data sets with one or more historical data sets.
9. The apparatus as claimed in claim 1 , wherein the plurality of data sets corresponds to different users of a single device.
10. The apparatus as claimed in claim 1 , wherein the plurality of data sets correspond to a single user of different respective devices.
11. The apparatus as claimed in claim 1 , wherein the data sets represent sensed health or activity data.
12. The apparatus as claimed in claim 11 , wherein the one or more devices are portable health monitoring devices and wherein the data sets are received wirelessly from one or more health monitoring devices.
13. The apparatus as claimed in claim 1 , wherein the apparatus is a hub device.
14. A method comprising:
receiving, via a local network, a plurality of data sets representing sensed data from one or more devices;
determining, using one or more local learned models, local parameters based on the received data sets;
generating a combined data set by combining the plurality of data sets;
determining, using one or more local learned models, global parameters based on the combined data set;
causing transmittal of, to a remote system, via a different network than the local network via which the plurality of the data sets are received, the global parameters for determining updated global parameters using one or more global learned models based at least partially on the global parameters;
receiving, from the remote system, the updated global parameters; and
updating the one or more local learned models using both the local parameters and updated global parameters.
15. A non-transitory computer readable medium comprising program instructions stored thereon for performing at least the following:
receiving, via a local network, a plurality of data sets representing sensed data from one or more devices;
determining, using one or more local learned models, local parameters based on the received data sets;
generating a combined data set by combining the plurality of data sets;
determining, using one or more local learned models, global parameters based on the combined data set;
transmitting, to a remote system, and via a different network than the local network via which the plurality of the data sets are received, the global parameters for determining updated global parameters using one or more global learned models based at least partially on the global parameters;
receiving, from the remote system, the updated global parameters; and
updating the one or more local learned models using both the local parameters and updated global parameters.
16. The apparatus according to claim 1 , wherein the data sets and the sensed data are not transmitted to the remote system.
17. The method according to claim 14 , wherein the data sets and the sensed data are not transmitted to the remote system.
18. The non-transitory computer readable medium according to claim 15 , wherein the data sets and the sensed data are not transmitted to the remote system.