Autonomous machines through cloud, error corrections, and predictions
A mechanism is described for facilitating smart collection of data and smart management of autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and combining a first computation directed to be performed locally at a local computing device with a second computation directed to be performed remotely at a remote computing device in communication with the local computing device over the one or more networks, where the first computation consumes low power, wherein the second computation consumes high power.
1. An apparatus comprising:
one or more processors including a graphics processor;
a network interface to provide access with one or more networks; and
a memory to store data, the memory including a trained local convolutional neural network (CNN);
wherein the one or more processors are to:
to detect one or more sets of data from one or more sources, the one or more sets of data including data requiring a first computation; and
determine whether the first computation is to be performed locally at the apparatus utilizing the local CNN or is to be directed to be performed remotely at a remote computing device utilizing a remote CNN, the remote computing device being in communication with the apparatus over the one or more networks, wherein the determination is based on either or both of:
a complexity of the first computation, or
a level of confidence in a decision for the first computation using the local CNN.
2. The apparatus of claim 1 , wherein the one or more processors are to perform the first computation locally upon determining that the first computation is a simple computation consuming a low amount of power and are to direct the first computation to be performed remotely upon determining that the first computation is a complex computation consuming a high amount of power.
3. The apparatus of claim 1 , wherein the one or more processors detecting one or more sets of data include the one or more processors to detect one or more faults with the apparatus, and wherein the one or more processors are to trigger a local CNN-based diagnosis of the one or more faults, and are further to direct the one or more faults for a remote CNN-based diagnosis if results of the local CNN-based diagnosis lack sufficient confidence.
4. The apparatus of claim 1 , wherein the one or more processors are to combine a first set of data with a second set of data of the one or more sets of data, and wherein the one or more processors are further to issue one or more predictions based on the first and second sets of data.
5. The apparatus of claim 4 , wherein the first set of data comprises social media data obtained from one or more websites, wherein the second set of data comprises autonomous machine data, wherein the one or more predictions are used by the one or more processors to facilitate one or more decisions relating to the apparatus.
6. The apparatus of claim 4 , wherein the one or more processors are to analyze the one or more sets of data including the first set of data and the second set of data to offer a dynamically optimized map, wherein the map offers guidance for the apparatus including preferred routes.
7. The apparatus of claim 1 , wherein the apparatus comprises an autonomous machine including one or more of a vehicle, a device, and an equipment, wherein the one or more networks comprise a cloud network or the Internet, and wherein the graphics processor is co-located with an application processor on a common semiconductor package.
8. The apparatus of claim 1 , wherein the local CNN is a snapshot of the remote CNN.
9. A method comprising:
detecting one or more sets of data from one or more sources, the one or more sets of data including data requiring a first computation; and
determining whether the first computation is to be performed locally at a local computing device utilizing a trained local convolutional neural network (CNN) or is to be directed to be performed remotely at a remote computing device utilizing a remote CNN, the remote computing device being in communication with the local computing device over one or more networks, wherein the determination is based on either or both of:
a complexity of the first computation, or
a level of confidence in a decision for the first computation using the local CNN.
10. The method of claim 9 , further comprising:
performing the first computation locally upon determining that the first computation is a simple computation consuming a low amount of power; and
directing the first computation to be performed remotely upon determining that the first computation is a complex computation consuming a high amount of power.
11. The method of claim 9 , wherein detecting one or more sets of data includes detecting one or more faults with the local computing device, and further comprising:
triggering a local CNN-based diagnosis of the one or more faults; and
directing the one or more faults for a remote CNN-based diagnosis if results of the local CNN-based diagnosis lack sufficient confidence.
12. The method of claim 9 , further comprising:
combining a first set of data with a second set of data of the one or more sets of data; and
issuing one or more predictions based on the first and second sets of data.
13. The method of claim 12 , wherein the first set of data comprises social media data obtained from one or more websites, wherein the second set of data comprises autonomous machine data, and wherein the one or more predictions are used to facilitate one or more decisions relating to the local computing device.
14. The method of claim 12 , further comprising analyzing the one or more sets of data including the first set of data and the second set of data to offer a dynamically optimized map, wherein the map offers guidance for the local computing device including preferred routes.
15. The method of claim 9 , wherein the local computing device comprises an autonomous machine including one or more of a vehicle, a device, and an equipment, wherein the one or more networks comprise a cloud network or the Internet, and wherein the autonomous machine comprises one or more processors including a graphics processor, wherein the graphics processor is co-located with an application processor on a common semiconductor package.
16. At least one non-transitory machine-readable medium comprising instructions that when executed by a local computing device, cause the local computing device to perform operations comprising:
detecting one or more sets of data from one or more sources, the one or more sets of data including data requiring a first computation; and
determining whether the first computation is to be performed locally at the local computing device utilizing a trained local convolutional neural network (CNN) or is to be directed to be performed remotely at a remote computing device utilizing a remote CNN, the remote computing device being in communication with the local computing device over one or more networks, wherein the determination is based on either or both of:
a complexity of the first computation, or
a level of confidence in a decision for the first computation using the local CNN.
17. The non-transitory machine-readable medium of claim 16 , further comprising instructions for:
performing the first computation locally upon determining that the first computation is a simple computation consuming a low amount of power; and
directing the first computation to be performed remotely upon determining that the first computation is a complex computation consuming a high amount of power.
18. The non-transitory machine-readable medium of claim 16 , wherein detecting one or more sets of data includes detecting one or more faults with the local computing device, and further comprising instructions for:
triggering a local CNN-based diagnosis of the one or more faults; and
directing the one or more faults for a remote CNN-based diagnosis if results of the local CNN-based diagnosis lack sufficient confidence.
19. The non-transitory machine-readable medium of claim 16 , further comprising instructions for:
combining a first set of data with a second set of data of the one or more sets of data; and
issuing one or more predictions based on the first and second sets of data.
20. The non-transitory machine-readable medium of claim 19 , wherein the first set of data comprises social media data obtained from one or more websites, wherein the second set of data comprises autonomous machine data, and wherein the one or more predictions are used to facilitate one or more decisions relating to the local computing device.
21. The non-transitory machine-readable medium of claim 19 , further comprising instructions for analyzing the one or more sets of data including the first set of data and the second set of data to offer a dynamically optimized map, wherein the map offers guidance for the local computing device including preferred routes, wherein the local computing device comprises an autonomous machine including one or more of a vehicle, a device, and an equipment, wherein the one or more networks comprise a cloud network or the Internet, and wherein the autonomous machine comprises one or more processors including a graphics processor, wherein the graphics processor is co-located with an application processor on a common semiconductor package.