System and method for automated learning from sensors
A computer-implemented method includes receiving first inputs associated with a first modality and second inputs associated with a second modality; processing the received first and second inputs with convolutional neural networks (CNN), wherein a set of first weights are used to handle the first inputs and a second set of weights are used to handle the second inputs; determining a loss for each of the first and the second inputs based on a loss function that applies the first set of weights, the second set of weights, and a presence of a co-occurrence; generating a shared feature space as an output of the CNNs, wherein a distance between cells associated with the first inputs and the second inputs in the shared feature space is determined based on the loss associated with each of the first inputs and the second inputs; and based on the shared feature space, providing an output.
1. A computer-implemented method, comprising:
receiving first inputs associated with a first modality, and second inputs associated with a second modality;
processing the received first inputs and second inputs in a convolutional neural network (CNN), wherein a first set of weights are assigned to the first inputs and a second set of weights are assigned to the second inputs, wherein text labeling is not performed, the first inputs are not converted to the second mode, and the second inputs are not converted to the first mode;
determining a loss for each of the first inputs and the second inputs based on a loss function that applies the first set of weights, the second set of weights, and a presence of a co-occurrence, wherein the co-occurrence is associated with the first inputs and the second inputs in sequence within a common time window;
generating a shared feature space as an output of the CNN, wherein a distance between cells associated with the first inputs and the second inputs in the shared feature space is determined based on the loss associated with each of the first inputs and the second inputs; and
based on the shared feature space, providing an output indicative of a classification or probability of a classification.
2. The computer-implemented method of claim 1 , wherein a first anchor channel is associated with the first modality and a second anchor channel is associated with the second modality.
3. The computer-implemented method of claim 1 , wherein the first modality comprises a visual mode and the second modality comprises an audio mode.
4. The computer-implemented method of claim 1 , wherein the first inputs and the second inputs are received from one or more sensors.
5. The computer-implemented method of claim 4 , wherein the one or more sensors comprise at least one of a camera associated with the first inputs and a microphone associated with the second inputs.
6. The computer-implemented method of claim 1 , wherein the computer-implemented method is executed in a neural processing unit of a processor.
7. The computer-implemented method of claim 1 , wherein the computer-implemented method is executed in a mobile communications device, a home management device, and/or a processor of a robotic device.
8. A non-transitory computer readable medium having a storage that stores instructions, the instructions executed by a processor, the instructions comprising:
receiving first inputs associated with a first modality, and second inputs associated with a second modality;
processing the received first inputs and second inputs in a convolutional neural network (CNN), wherein a first set of weights are assigned to the first inputs and a second set of weights are assigned to the second inputs, wherein text labeling is not performed, the first inputs are not converted to the second mode, and the second inputs are not converted to the first mode;
determining a loss for each of the first inputs and the second inputs based on a loss function that applies the first set of weights, the second set of weights, and a presence of a co-occurrence, wherein the co-occurrence is associated with the first inputs and the second inputs in sequence within a common time window;
generating a shared feature space as an output of the CNN, wherein a distance between cells associated with the first inputs and the second inputs in the shared feature space is determined based on the loss associated with each of the first inputs and the second inputs; and based on the shared feature space, providing an output indicative of a co-occurrence or not.
9. The computer-implemented method of claim 8 , wherein the first modality comprises a visual mode and the second modality comprises an audio mode.
10. The computer-implemented method of claim 8 , wherein the first inputs and the second inputs are received from one or more sensors, and wherein the one or more sensors comprise at least one of a camera associated with the first inputs and a microphone associated with the second inputs.
11. The computer-implemented method of claim 8 , wherein the computer-implemented method is executed in a mobile communications device, a home management device, and/or a processor of a robotic device.