System and method for learning sensory media association without using text labels

1. A computer-implemented method of learning sensory media association, comprising:

receiving a first type of nontext input and a second type of nontext input;

encoding and decoding the first type of nontext input using a first autoencoder having a first convolutional neural network, and the second type of nontext input using a second autoencoder having a second convolutional neural network;

bridging first autoencoder representations and second autoencoder representations by a first deep neural network that learns mappings from the first autoencoder representations associated with a first modality to the second autoencoder representations associated with a second modality and a second deep neural network that learns mappings from the second autoencoder representations associated with the second modality to the first autoencoder representations associated with the first modality, wherein the second deep neural network is different from the first deep neural network; and

based on the encoding, decoding, and the bridging, generating a first type of nontext output and a second type of nontext output based on the first type of nontext input or the second type of nontext input in either the first modality or the second modality.

2. The computer-implemented method of claim 1 , wherein the first type of nontext input is audio, and the second type of nontext input is an image.

3. The computer-implemented method of claim 2 , wherein the audio is sensed by a microphone and the image is sensed by a camera.

4. The computer-implemented method of claim 1 , wherein the first type of nontext input is one of audio, image, temperature, touch, and radiation, and the second type of nontext input is another of audio, image, temperature, touch, and radiation.

5. The computer-implemented method of claim 1 , wherein the first type of nontext input and the second type of nontext input are provided to an autonomous robot for training.

6. The computer-implemented method of claim 1 , wherein text labels are not used, and the receiving, encoding, decoding, bridging and generating are language-independent.

7. The computer-implemented method of claim 1 , wherein a third type of nontext input is received, the third type of nontext input is encoded using a third autoencoder having a third convolutional neural network, the third autoencoder is bridged to the first autoencoder and the second autoencoder by the deep neural network that learns mappings between the third type of representation associated with a third modality and the first type of representation and the second type of representation, and a third type of nontext output is generated, without requiring a retraining of the first autoencoder, the second autoencoder, the first convolutional neural network and the second convolutional neural network.

8. A non-transitory computer readable medium having executable instructions stored in a storage and executed on a processor, the instructions comprising:

receiving a first type of nontext input and a second type of nontext input;

encoding and decoding the first type of nontext input using a first autoencoder having a first convolutional neural network, and the second type of nontext input using a second autoencoder having a second convolutional neural network;

bridging first autoencoder representations and second autoencoder representations by a first deep neural network that learns mappings from the first autoencoder representation associated with a first modality to the second autoencoder representation associated with a second modality and a second deep neural network that learns mappings from the second autoencoder representations associated with the second modality to the first autoencoder representations associated with the first modality; and

based on the encoding, decoding, and the bridging, generating a first type of nontext output and a second type of nontext output based on the first type of nontext input or the second type of nontext input in either the first modality or the second modality.

9. The non-transitory computer readable medium of claim 8 , wherein the first type of nontext input is audio, and the second type of nontext input is an image.

10. The non-transitory computer readable medium of claim 9 , wherein the audio is sensed by a microphone and the image is sensed by a camera.

11. The non-transitory computer readable medium of claim 8 , wherein the first type of nontext input is one of audio, image, temperature, touch, and radiation, and the second type of nontext input is another of audio, image, temperature, touch, and radiation.

12. The non-transitory computer readable medium of claim 8 , wherein the first type of nontext input and the second type of nontext input are provided to an autonomous robot for training.

13. The non-transitory computer readable medium of claim 8 , wherein text labels are not used, and the receiving, encoding, decoding, bridging and generating are language-independent.

14. The non-transitory computer readable medium of claim 8 , wherein a third type of nontext input is received, the third type of nontext input is encoded using a third autoencoder having a third convolutional neural network, the third autoencoder is bridged to the first autoencoder and the second autoencoder by the deep neural network that learns mappings between the third type of representation associated with a third modality and the first type of representation and the second type of representation, and a third type of nontext output is generated, without requiring a retraining of the first autoencoder, the second autoencoder, the first convolutional neural network and the second convolutional neural network.

15. A computer-implemented system for learning sensory media association, comprising:

a first type of sensor receiving a first type of nontext input and a second type of sensor receiving a second type of nontext input;

a processor, that receives the first type of nontext input and the second type of nontext input, encodes and decodes of the first type of nontext input using a first autoencoder having a first convolutional neural network, and the second type of nontext input using a second autoencoder having a second convolutional neural network, and bridges first autoencoder representations and second autoencoder representations by a first deep neural network that learns mappings from the first autoencoder representation associated with a first modality to the second autoencoder representation associated with a second modality and a second deep neural network that learns mappings from the second autoencoder representations associated with the second modality to the first autoencoder representations associated with the first modality; and

an output device that, based on the encoding, decoding, and the bridging, generates a first type of nontext output and a second type of nontext output based on the first type of nontext input or the second type of nontext input in either the first modality or the second modality.

16. The computer-implemented system of claim 15 , wherein the first type of sensor is a microphone and the second type of sensor is a camera.

17. The computer-implemented system of claim 15 , wherein the first type of nontext input is one of audio, image, temperature, touch, and radiation, and the second type of nontext input is another of audio, image, temperature, touch, and radiation.

18. The computer-implemented system of claim 15 , wherein the first type of nontext input and the second type of nontext input are provided to an autonomous robot for training.

19. The computer-implemented system of claim 15 , wherein text labels are not used, and the receiving, encoding, decoding, bridging and generating are language-independent.

20. The computer-implemented system of claim 15 , wherein a third type of nontext input is received, the third type of nontext input is encoded using a third autoencoder having a third convolutional neural network, the third autoencoder is bridged to the first autoencoder and the second autoencoder by the deep neural network that learns mappings between the third type of representation associated with a third modality and the first type of representation and the second type of representation, and a third type of nontext output is generated, without requiring a retraining of the first autoencoder, the second autoencoder, the first convolutional neural network and the second convolutional neural network.