CPC G06N 3/04 (2013.01) [G06F 1/3246 (2013.01); G06F 1/3287 (2013.01); G06F 21/6209 (2013.01)] | 19 Claims |
1. A computer-implemented method for power saving and encryption during analysis of media captured by an information capture device using a partitioned neural network, the computer-implemented method comprising:
replicating, by an information capture device, an artificial neural network (ANN) from a computer server to the information capture device, wherein the ANN on the computer server and a replicated ANN on the information capture device, both, include M layers;
in response to captured data being input to be processed, selecting, by the information capture device, a first k layers to execute on the information capture device, and transmitting a value of k to the computer server;
in response to captured data being input to be processed, partially processing, by the information capture device, the captured data by executing the first k layers using the replicated ANN, wherein only the k layers are selected to execute on the information capture device; and
transmitting, by the information capture device, an output of the k-th layer to the computer server, which partially processes the captured data by executing the remainder of the M layers using the ANN and the output of the k-th layer,
wherein the value of k is selected by the information capture device based at least in part on a charge-level of a power source of the information capture device.
|