Offline detector

1. An integrated circuit for signal detection in an offline state, comprising:

a host processor coupled with a co-processor and configured to receive a signal stream;

wherein the signal stream comprises signals received by at least one of: an infrared sensor, a pressure sensor, a temperature sensor, a proximity sensor, a motion sensor, a fingerprint scanner, a photo eye sensor, a microphone, and a wireless signal antenna;

the co-processor configured to perform one or more recognition tasks via a recognition network and transmit one or more results to the host processor;

wherein the co-processor includes a neural network configured to identify one or more target signals from the received signal stream; and

wherein the one or more target signals may be detected using a set of weights in absence of a connection to an external communications network, wherein the host processor is configured to receive weighting signals from the co-processor, and transmit the one or more target signals indicating detection of desired user-specified signals.

2. The integrated circuit of claim 1 , wherein the one or more target signals are comprised of any of spoken keywords, specific sounds, desired image types or classes, and signal patterns among sensor data.

3. The integrated circuit of claim 1 , wherein the set of weights are stored in a memory storage that is accessible to the integrated circuit.

4. The integrated circuit of claim 1 , wherein the set of weights comprises a programmed file that is formed by way of training an external software model of the artificial neural network to recognize the one or more target signals.

5. The integrated circuit of claim 1 , wherein the offline state is comprised of an absence of connectivity between the integrated circuit and an external communications network, such as the Internet, the cloud.

6. A method for generating a weight file that causes an integrated circuit to detect desired user-specified signals, comprising:

listing desired target signals that may be detected by a signal detector;

retrieving one or more signal databases that are comprised of standard target signals that may be detected by the signal detector;

combining the desired target signals and the one or more signal databases to build a modified database;

using the modified database to train a neural network implementation to recognize the target signals and the standard signals;

producing a set of weights by way of training the neural network implementation; and

translating the set of weights into the weight file suitable for being stored in a memory storage that is accessible to the integrated circuit;

receiving, by a host processor, the set of weights from a co-processor configured to perform one or more recognition tasks for the host processor and transmitting one or more signals indicating detection of the desired user-specific signals;

wherein the weight file is used to detect the desired user-specific signals received from at least one of: an infrared sensor, a microphone, a pressure sensor, a temperature sensor, a proximity sensor, a motion sensor, a fingerprint scanner, a photo eye sensor, and a wireless signal antenna.

7. The method of claim 6 , wherein listing comprises entering the target signals into a web-based application that is configured to generate the weight file.

8. The method of claim 6 , wherein listing comprises entering the target signals into a cloud-based application that is configured to generate the weight file.

9. The method of claim 6 , wherein listing comprises entering the target signals into a stand-alone software that is configured to generate the weight file.

10. The method of claim 6 , wherein the target signals may be any type of signal that an end-user wants to detect.

11. The method of claim 6 , wherein combining comprises labeling the target signals with corresponding labels and labeling all other signals by way of a generic label.

12. The method of claim 6 , wherein the neural network implementation is a software model of a neural network that is implemented in the integrated circuit comprising the signal detector.

13. The method of claim 6 , wherein the weight file may be provided to an end-user upon purchasing a mobile device.

14. The method of claim 6 , wherein the weight file may be programmed into one or more chips that may be purchased by an end-user for use in a mobile device.

15. The method of claim 6 , wherein upon an end-user installing the weight file the mobile device, the signal detector may detect the target signals by way of the set of weights.

16. The method of claim 15 , wherein the signal detector continues detecting the target signals in an offline state comprised of an absence of connectivity between the signal detector and an external communications network, such as the Internet, the cloud.

17. A system for signal detection in an offline state, comprising:

a host processor coupled with a co-processor and configured to receive a signal stream;

wherein the one or more signals are received by at least one of: an infrared sensor, a microphone, a pressure sensor, a temperature sensor, a proximity sensor, a motion sensor, a fingerprint scanner, a photo eye sensor, and a wireless signal antenna;

the co-processor configured to perform one or more recognition tasks and transmit one or more results to the host processor, the co-processor including an artificial neural network that is configured to identify one or more target signals among the one or more signals;

wherein the one or more recognition tasks are performed using the artificial neural network;

a communications interface between the host processor and the co-processor configured to transmit information therebetween; and

wherein the one or more target signals may be identified using a set of weights, and wherein the host processor is configured to receive weighting signals from the co-processor, and transmit the one or more target signals indicating detection of desired user-specified signals.