Abstract: A method includes obtaining a batch of training data including multiple paired image-text pairs and multiple unpaired image-text pairs, where each paired image-text pair and each unpaired image-text pair includes an image and a text. The method also includes training a machine learning model using the training data based on an optimization of a combination of losses. The losses include, for each paired image-text pair, (i) a first multi-modal representation loss based on the paired image-text pair and (ii) a second multi-modal representation loss based on two or more unpaired image-text pairs, selected from among the multiple unpaired image-text pairs, wherein each of the two or more unpaired image-text pairs includes either the image or the text of the paired image-text pair.

Abstract: A method includes obtaining a batch of training data including multiple paired image-text pairs and multiple unpaired image-text pairs, where each paired image-text pair and each unpaired image-text pair includes an image and a text. The method also includes training a machine learning model using the training data based on an optimization of a combination of losses. The losses include, for each paired image-text pair, (i) a first multi-modal representation loss based on the paired image-text pair and (ii) a second multi-modal representation loss based on two or more unpaired image-text pairs, selected from among the multiple unpaired image-text pairs, wherein each of the two or more unpaired image-text pairs includes either the image or the text of the paired image-text pair.

Abstract: A machine learning method using a trained machine learning model residing on an electronic device includes receiving an inference request by the electronic device. The method also includes determining, using the trained machine learning model, an inference result for the inference request using a selected inference path in the trained machine learning model. The selected inference path is selected based on a highest probability for each layer of the trained machine learning model. A size of the trained machine learning model is reduced corresponding to constraints imposed by the electronic device. The method further includes executing an action in response to the inference result.

Abstract: A continual learning method includes obtaining an input data including a trained model, continual learning (CL) Information, and training data by an electronic device. The method also includes re-training, using the electronic device, the model for a task based on the training data. The method also includes updating, using the electronic device, the CL Information based on the model and the training data. The method further includes selecting a first set of exemplars from the training data based on data associated with the CL Information. The CL Information includes a first group of variables associated with the model and a second group of variables associated with the model that changes to the first group of variables have stronger impact to the model's performance of the task than changes to the second group of variables.

Abstract: A wearable filtrating artificial kidney device, comprising a transfusion inlet (2), a blood pump (3), an arterial pressure detector (4), a blood filter (7), a venous pressure detector (8) and an air detector (9), wherein the transfusion inlet (2), the blood pump (3), the arterial pressure detector (4), a resin hemoperfusion apparatus (5), an active carbon hemoperfusion apparatus (6), the blood filter (7), the venous pressure detector (8) and the air detector (9) are connected sequentially; a liquid waste outlet of the blood filter (7) is connected with an ultrafiltration control pump (10). Glomerulus filtration can be simulated to achieve the goal of removing toxins and excessive moisture in the blood by virtue of ultrafiltration of the blood filter (7). A dialyzate and a complicated dialyzate circulating device are not used for the device, so that the volume and weight of the device can be reduced greatly, and the device can be worn conveniently.

Abstract: A wearable filtrating artificial kidney device, comprising a transfusion inlet (2), a blood pump (3). an arterial pressure detector (4), a blood filter (7), a venous pressure detector (8) and an air detector (9), wherein the transfusion inlet (2), the blood pump (3), the arterial pressure detector (4), a resin hemoperfusion apparatus (5), an active carbon hemoperfusion apparatus (6), the blood filter (7), the venous pressure detector (8) and the air detector (9) are connected sequentially; a liquid waste outlet of the blood filter (7) is connected with an ultrafiltration control pump (10). Glomerulus filtration can be simulated to achieve the goal of removing toxins and excessive moisture in the blood by virtue of ultrafiltration of the blood filter (7). A dialyzate and a complicated dialyzate circulating device are not used for the device, so that the volume and weight of the device can be reduced greatly, and the device can be worn conveniently.