Controller systems and methods of limiting the operation of neural networks to be within one or more conditions

• US 10,324,467 B1
• Filed: 05/29/2018
• Issued: 06/18/2019
• Est. Priority Date: 12/29/2017
• Status: Active Grant

• Current Assignee: Apex AI Industries LLC
• Original Assignee: Apex Artificial Intelligence Industries, Inc.
• Inventors: Abeloe, Kenneth A.
• Primary Examiner(s): Tzeng, Feng-Tzer
• Application Number:
  US15/991,769
• Publication Number:
  US 20190204832A1
• Time in Patent Office: 385 Days
• CPC Class Codes: B60Q 5/006 indicating risk of collision between vehicles or with pedestrians
• CPC Class Codes: B60R 11/0217 for loud-speakers
• CPC Class Codes: B60R 11/04 Mounting of cameras operative during drive; Arrangement of controls thereof relative to the vehicle
• CPC Class Codes: B60R 2300/102 using 360 degree surveillance camera system
• CPC Class Codes: B60R 2300/103 using camera systems provided with artificial illumination device, e.g. IR light source
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/047 Probabilistic or stochastic networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/047 Architecture of speech synthesisers
• CPC Class Codes: G10L 15/16 : using artificial neural networks
• CPC Class Codes: G10L 15/22 : Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 : Execution procedure of a spoken command

Abstract

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.

Claims

1. An apparatus having a plurality of components, comprising:

an input device constructed to generate an input data vector;

a first neural network trained to generate an output to control the apparatus by processing the input data vector;

a second neural network configured to receive the output from the first neural network, the second neural network trained to determine whether the output of the first neural network corresponds to a predetermined condition and generate a control output from the output of the first neural network; and

a processor configured to;

receive the control output from the second neural network, and

in response to the control output indicating the output of the first neural network corresponds to a predetermined condition, control an operation of the first neural network, and not using the output from the first neural network to control the apparatus.

2. The apparatus of claim 1, wherein the control of an operation of the first neural network comprises terminating the operation of the first neural network when the output of the first neural network corresponds to a predetermined condition.

3. The apparatus of claim 1, wherein the control of an operation of the first neural network comprises re-training the first neural network when the output of the first neural network corresponds to a predetermined condition.

4. The apparatus of claim 3, wherein the processor is further configured to re-train the first neural network using the input data vector generated by the input device.

5. The apparatus of claim 1, further comprising:

a third neural network, configured to provide a second output to the second neural network, structured and trained substantially identical to the first neural network to generate the second output by processing the input data vector,

wherein the second neural network is further trained to compare the output from the first neural network and the second output from the third neural network, and detect a difference between the output from the first neural network and the second output from the third neural network, and

wherein the processor is further configured to perform a control action if the detected difference corresponds to a predetermined level.

6. The apparatus of claim 5, wherein the processor is further configured to terminate the operation of the first neural network if the detected difference is above the predetermined level.

7. The apparatus of claim 5, wherein the processor is further configured to re-train the first neural network if the detected difference is above the predetermined level.

8. The apparatus 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 message to control the autonomous land vehicle.

20. The apparatus of claim 1, wherein the control of the operation of the first neural network comprises not providing the output of the first neural network to the processor when the output of the first neural network corresponds to a predetermined condition.

9. A computer-implemented method of controlling an apparatus, the method comprising:

processing an input data vector using a first neural network trained to generate an output by inferencing on the input data vector;

controlling an operation of an aspect of the apparatus using the output from the first neural network;

generating a control output using a second neural network trained to generate the control output by inferencing on the output generated by the first neural network, the control output indicating the output generated by the first neural network corresponds to a predetermined condition; and

in response to the first neural network output corresponding to the predetermined condition, controlling an operation of the first neural network using the control output from the second neural network and not controlling an operation of the apparatus using the output from the first neural network,

wherein the method is performed by one or more computer hardware processors configured to execute computer-executable instructions on a non-transitory computer storage medium.

10. The computer-implemented method of claim 9, wherein controlling an operation of the first neural network comprises terminating the first neural network when the output is determined to correspond to the predetermined condition.

11. The computer-implemented method of claim 9, wherein controlling an operation of the first neural network comprises re-training the first neural network when the output is determined to correspond to the predetermined condition.

12. The computer-implemented method of claim 9, wherein controlling an operation of the first neural network comprises generating a human recognizable notification in response to determining the output corresponds to the predetermined condition.

13. The computer-implemented method of claim 9, wherein the predetermined condition is a condition that prevents damage to the apparatus.

14. The computer-implemented method of claim 9, further comprising:

receiving, from a machine recognizable human speech part, information identifying the predetermined condition; and

defining the predetermined condition based at least in part on the information received from the machine recognizable human speech part.

15. The computer-implemented method of claim 9, wherein the apparatus is a human speech generator comprising a loudspeaker, and controlling the operation using the output includes generating human speech parts to be played on the loudspeaker.

16. The computer-implemented method of claim 9, wherein the apparatus is an autonomous land vehicle, and controlling the operation using the output includes generating a signal to control an autonomous land vehicle based at least in part on the output.

17. The computer-implemented method of claim 9, wherein the apparatus comprises an image generator.

18. An apparatus having a plurality of components, the apparatus comprising:

an input device constructed to generate an input data vector;

a first neural network trained to generate an output to control the apparatus by processing the input data vector;

a second neural network configured to receive the output from the first neural network, the second neural network structured and trained to determine whether the output corresponds to a predetermined condition and generate a control output; and

a processor configured to receive the control output from the second neural network and to control an operation of the first neural network using the control output from the second neural network and not control the apparatus using the output from the first neural network in response to determining the output of the first neural network corresponds to the predetermined condition.

19. The apparatus of claim 18, wherein the processor is further configured to terminate the first neural network when the second neural network determines the output from the first neural network corresponds to the predetermined condition.