Abstract: Neural networks and learning algorithms can use a variance of gradients to provide a heuristic understanding of the model. The variance of gradients can be used in active learning techniques to train a neural network. Techniques include receiving a dataset with a vector. The dataset can be annotated and a loss calculated. The loss value can be used to update the neural network through backpropagation. An updated dataset can be used to calculate additional losses. The loss values can be added to a pool of gradients. A variance of gradients can be calculated from the pool of gradient vectors. The variance of gradients can be used to update a neural network.

Abstract: A deep neural network (DNN) can be trained based on a first training dataset that includes first images including annotated first objects. The DNN can be tested based on the first training dataset to determine first object predictions including first uncertainties. The DNN can be tested by inputting a second training dataset and outputting first object predictions including second uncertainties, wherein the second training dataset includes second images including unannotated second objects. A subset of images included in the second training dataset can be selected based on the second uncertainties, The second objects in the selected subset of images included in the second training dataset can be annotated. The DNN can be trained based on the selected subset of images included in the second training dataset including the annotated second objects.

Abstract: An exemplary system and method for contrastive learning that can generate pseudo severity-based labels for unlabeled medical images using gradient measures from an anomaly detection operation. The severity labels can be then used for diagnosis of a disease or medical condition or as labels for as a training data set for training of another machine learning model. The training can be performed in combination with biomarker data.

Abstract: An exemplary system and method that facilitate the use of clinical medical data in electronic medical records for training an AI model. In an aspect, the exemplary system and method can be used for asymmetric multi-modal machine learning training, e.g., supervised contrastive learning, on one data set modality (e.g., having clinical labels) to learn useful features in a first model for fine-tuning on another data set (e.g., having biomarker labels). In another aspect, the exemplary system and method can use demographic information in electronic medical records for training an AI model.

Abstract: A deep neural network (DNN) can be trained based on a first training dataset that includes first images including annotated first objects. The DNN can be tested based on the first training dataset to determine first object predictions including first uncertainties. The DNN can be tested by inputting a second training dataset and outputting first object predictions including second uncertainties, wherein the second training dataset includes second images including unannotated second objects. A subset of images included in the second training dataset can be selected based on the second uncertainties, The second objects in the selected subset of images included in the second training dataset can be annotated. The DNN can be trained based on the selected subset of images included in the second training dataset including the annotated second objects.

Abstract: In a method for determining if a test data set is anomalous in a deep neural network that has been trained with a plurality of training data sets resulting in back propagated training gradients having statistical measures thereof, the test data set is forward propagated through the deep neural network so as to generate test data intended labels including at least original data, prediction labels, and segmentation maps. The test data intended labels are back propagated through the deep neural network so as to generate a test data back propagated gradient. If the test data back propagated gradient differs from one of the statistical measures of the back propagated training gradients by a predetermined amount, then an indication that the test data set is anomalous is generated. The statistical measures of the back propagated training gradient include a quantity including an average of all the back propagated training gradients.

Abstract: Neural networks and learning algorithms can use a variance of gradients to provide a heuristic understanding of the model. The variance of gradients can be used in active learning techniques to train a neural network. Techniques include receiving a dataset with a vector. The dataset can be annotated and a loss calculated. The loss value can be used to update the neural network through backpropagation. An updated dataset can be used to calculate additional losses. The loss values can be added to a pool of gradients. A variance of gradients can be calculated from the pool of gradient vectors. The variance of gradients can be used to update a neural network.

Abstract: A portable computing device equipped with at least one image capture device and/or a light source captures an image (or a video) of a portion of a surface of interest having the damage that is exposed to a light from the light source. The portable computing device converts the image to an output image that highlights the damage. If the damage is a dent, the image is converted to a false color image using a saliency algorithm. If the damage is a scratch, the image is converted to a colorspace stretched image using color stretching algorithms. The size of the damage is determined by capturing an image of a ruler placed adjacent to the damage and the portion of surface of interest having the damage. The ruler is then removed from the image. The resulting image is converted to the output image. The ruler is added to the output image.

Abstract: A portable computing device equipped with an image capture device captures an image of a vehicle dashboard of a vehicle. Then, the portable computing device identifies the location of one or more components of the vehicle dashboard in the captured image. Based on the location of the one or more components, the portable computing device segments the captured image to obtain an image of each of the one or more components. Further, the portable computing device processes the images of the one or more components using one or more machine learning models to determine a reading associated with each of the one or more components. An accuracy of the readings is verified and responsively, the portable computing device inputs the readings in respective data fields of an electronic form. The readings associated with the one or more components of the vehicle dashboard represent data associated with the vehicle.

Abstract: A portable computing device equipped with an image capture device captures an image of a vehicle dashboard of a vehicle. Then, the portable computing device identifies the location of one or more components of the vehicle dashboard in the captured image. Based on the location of the one or more components, the portable computing device segments the captured image to obtain an image of each of the one or more components. Further, the portable computing device processes the images of the one or more components using one or more machine learning models to determine a reading associated with each of the one or more components. An accuracy of the readings is verified and responsively, the portable computing device inputs the readings in respective data fields of an electronic form. The readings associated with the one or more components of the vehicle dashboard represent data associated with the vehicle.

Abstract: A portable computing device equipped with at least one image capture device and/or a light source captures an image (or a video) of a portion of a surface of interest having the damage that is exposed to a light from the light source. The portable computing device converts the image to an output image that highlights the damage. If the damage is a dent, the image is converted to a false color image using a saliency algorithm. If the damage is a scratch, the image is converted to a colorspace stretched image using color stretching algorithms. The size of the damage is determined by capturing an image of a ruler placed adjacent to the damage and the portion of surface of interest having the damage. The ruler is then removed from the image. The resulting image is converted to the output image. The ruler is added to the output image.