Controller systems and methods of limiting the operation of neural networks to be within one or more conditions
View Patent ↗Systems and methods for automatically self-correcting or correcting in real-time one or more neural networks after detecting a triggering event, or breaching boundary conditions are provided. Such a triggering event may indicate incorrect output signal or data being generated by the one or more neural networks. In particular, machine controllers of the invention limit the operations of neural networks to be within boundary conditions. Autonomous machines of the invention can be self-corrected after a breach of a boundary condition is detected. Autonomous land vehicles of the invention are capable of determining the timing of automatic transition to the manual control from automated driving mode. The controller of the invention filters and saves input-output data sets that fall within boundary conditions for later training of neural networks. The controllers of the invention include security architectures to prevent damages from virus attacks or system malfunctions.
1. A method of operating an apparatus using a control system that includes at least one neural network, comprising:
receiving an input vector captured by the apparatus;
processing the input vector using the at least one neural network of the control system;
obtaining an output from the at least one neural network resulting from processing the input vector;
processing the output with a second neural network to determine whether the output breaches a predetermined condition that is unchangeable after an initial installation onto the control system, wherein the second neural network is prevented from being retrained; and
using the output from the at least one neural network to control the apparatus unless the output breaches the predetermined condition.
2. The method of claim 1 , further comprising re-training the at least one neural network when the output is determined to breach the predetermined condition.
3. The method of claim 1 , further comprising defining the predetermined condition to prevent a damage to the apparatus.
4. The method of claim 1 , further comprising defining the predetermined condition with a machine recognizable human speech part.
5. The method of claim 1 , wherein the apparatus is a human speech generator with a loudspeaker and the step of using the obtained output further includes the step of generating human speech parts to be played on the loudspeaker.
6. The method of claim 1 , wherein the apparatus is an autonomous land vehicle and the step of using the obtained output further includes the step of generating a signal to control the autonomous land vehicle.
7. The method of claim 1 , further comprising:
in response to determining the obtained output from the at least one neural network breaches a predetermined condition, replacing nodal values of the at least one neural network with previously stored nodal values.
8. An apparatus being operated in part by a controller, the apparatus comprising:
an input device coupled to the apparatus, the input device constructed to generate an input vector;
a controller;
at least one neural network coupled to the controller, the at least one neural network constructed to receive the input vector and to generate an output; and
wherein the controller comprises a second neural network constructed to receive the output from the at least one neural network and determine whether the output breaches a predetermined condition unchangeable after an initial installation onto the controller,
wherein the second neural network is prevented from being retrained, and
wherein the controller is constructed to operate the apparatus using the output from the at least one neural network unless the output from the at least one neural network is determined to breach the predetermined condition.
9. The apparatus of claim 8 , wherein the controller is further constructed to re-train the at least one neural network when the output is determined to breach the predetermined condition.
10. The apparatus of claim 8 , wherein the controller is further constructed to generate a human recognizable notification when the output is determined to breach the predetermined condition.
11. The apparatus of claim 8 , wherein the predetermined condition is defined to prevent damage to the apparatus.
12. The apparatus of claim 8 , wherein the predetermined condition is defined with a machine recognizable human speech part.
13. The apparatus of claim 8 , wherein the apparatus is an autonomous land vehicle coupled to the at least one neural network and constructed to generate a signal to control the autonomous land vehicle.
14. The apparatus of claim 8 , wherein nodal values of the at least one neural network are replaced by to a previously stored nodal values when the obtained output from the at least one neural network is determined to breach a predetermined condition.
15. An apparatus being operated in part by a controller, comprising:
an input means coupled to the apparatus for generating an input vector;
at least one neural network coupled to the controller and constructed to receive the input vector and to generate an output; and
a second neural network coupled to the at least one neural network and constructed for comparing the output from the at least one neural network with a predetermined condition that is unchangeable after an initial installation onto the control system, wherein the second neural network is prevented from being retrained, and
wherein the controller is constructed to operate the apparatus using the output from the at least one neural network unless the output is determined, by the second neural network, to breach the predetermined condition.
16. The apparatus of claim 15 , wherein the apparatus is an autonomous land vehicle coupled to the at least one neural network, and the at least one neural network is constructed to generate a signal to control the autonomous land vehicle.
17. The method of claim 1 , wherein the at least one neural network is trained with a first data set and the second neural network is trained with a second data set, the second data set different than the first data set.
18. The apparatus of claim 8 , wherein the at least one neural network is trained with a first data set and the second neural network is trained with a second data set, the second data set different than the first data set.
19. The apparatus of claim 15 , wherein the at least one neural network is trained with a first data set and the second neural network is trained with a second data set, the second data set different than the first data set.