Abstract: A multi-modal artificial neural network and a self-supervised learning method for training that network. The learning method involves processing, using a first modality simple Siamese network, a pair of first modality augmented views of an input; processing, using a second modality simple Siamese network, a pair of second modality augmented views of the input; determining at least one cross-modal loss between the first and second modality simple Siamese networks; determining a total loss from: (i) first and second modality losses respectively determined during the processing using the first and second modality simple Siamese networks; and (ii) the at least one cross-modal loss; and training the first and second modality simple Siamese networks based on the total loss. The trained network may be used to analyze multi-modal content such as video content that has an audio track. A Multi-Modal Multi-Head Network (M3HN) may also be trained to process modality-specific and modality-agnostic representations.

Abstract: An apparatus for providing similar contents, using a neural network, includes a memory storing instructions, and a processor configured to execute the instructions to obtain a plurality of similarity values between a user query and a plurality of images, using a similarity neural network, obtain a rank of each the obtained plurality of similarity values, and provide, as a most similar image to the user query, at least one among the plurality of images that has a respective one among the plurality of similarity values that corresponds to a highest rank among the obtained rank of each of the plurality of similarity values. The similarity neural network is trained with a divergence neural network for outputting a divergence between a first distribution of first similarity values for positive pairs, among the plurality of similarity values, and a second distribution of second similarity values for negative pairs, among the plurality of similarity values.

Abstract: An apparatus for providing similar contents, using a neural network, includes a memory storing instructions, and a processor configured to execute the instructions to obtain a plurality of similarity values between a user query and a plurality of images, using a similarity neural network, obtain a rank of each the obtained plurality of similarity values, and provide, as a most similar image to the user query, at least one among the plurality of images that has a respective one among the plurality of similarity values that corresponds to a highest rank among the obtained rank of each of the plurality of similarity values. The similarity neural network is trained with a divergence neural network for outputting a divergence between a first distribution of first similarity values for positive pairs, among the plurality of similarity values, and a second distribution of second similarity values for negative pairs, among the plurality of similarity values.

Abstract: An image-guided therapy delivery system includes a therapy generator configured to generate a therapy beam directed to a time-varying therapy locus within a therapy recipient, an imaging input configured to receive imaging information about a time-varying target locus within the therapy recipient, and a therapy controller. The therapy generator includes a therapy output configured to direct the therapy beam according to a therapy protocol. The therapy controller is configured to automatically generate a predicted target locus using information indicative of an earlier target locus extracted from the imaging information, a cyclic motion model, and a specified latency, and automatically generate an updated therapy protocol to align the time-varying therapy locus with the predicted target locus.

Abstract: A medical system includes a medical device and a controller. The medical device is controlled according to a control protocol. The controller is configured to receive a measured data set containing a current value at a current time and past values at past times of a physiologic signal measured on a recipient, calculate a difference signal at the current time based on the measured data set, and predict a difference value using the difference signal and a prediction algorithm. The difference value is a difference between a predicted future value of the physiologic signal at a future time and the current value. The controller is further configured to calculate the predicted future value based on the difference value and the current value and update the control protocol according to the predicted future value.

Abstract: An image-guided therapy delivery system includes a therapy generator configured to generate a therapy beam directed to a time-varying therapy locus within a therapy recipient, an imaging input configured to receive imaging information about a time-varying target locus within the therapy recipient, and a therapy controller. The therapy generator includes a therapy output configured to direct the therapy beam according to a therapy protocol. The therapy controller is configured to automatically generate a predicted target locus using information indicative of an earlier target locus extracted from the imaging information, a cyclic motion model, and a specified latency, and automatically generate an updated therapy protocol to align the time-varying therapy locus with the predicted target locus.

Abstract: A medical system includes a medical device and a controller. The medical device is controlled according to a control protocol. The controller is configured to receive a measured data set containing a current value at a current time and past values at past times of a physiologic signal measured on a recipient, calculate a difference signal at the current time based on the measured data set, and predict a difference value using the difference signal and a prediction algorithm. The difference value is a difference between a predicted future value of the physiologic signal at a future time and the current value. The controller is further configured to calculate the predicted future value based on the difference value and the current value and update the control protocol according to the predicted future value.