Abstract: A computer-implemented method comprises linking a private AI model to a public AI model to thereby form a combined AI model comprising the private AI model and the public AI model; and training the combined AI model with private samples while keeping the public AI model fixed so that only the private AI model is trained with the private samples.

Abstract: A computer-implemented method generates a hamming code based target label for each class of a dataset in which hamming distance between the target labels in the dataset is maximized and trains a convolutional neural network with the hamming codes based target label to thereby produce a trained AI model. The confusability between classes of the dataset is determined using a confusion matrix. The hamming distances of classes of the dataset that are determined to be more confusable are set to higher values than the hamming distances of classes of the dataset that are determined to be less confusable.

Abstract: A pretrained model is selected to operate in an augmented model configuration with a submodel. The submodel is trained using training data corresponding to a second domain, whereas the pretrained model is trained to operate on data of a first domain. The pretrained model is augmented, to form the augmented model configuration, with the submodel, by combining a first feature map being output from a layer in the pretrained model with a second feature map being output from a layer in the submodel. The combining forms a combined feature map. The combined feature map is input into a different layer in the submodel.

Abstract: A method controls a remote robotic avatar based on a description of a physical object. A message transmitter transmits a message to a remote robotic avatar instructing the remote robotic avatar to identify a physical object at a remote second location, where an appearance of the physical object is described in the message. The message transmitter also transmits an instruction to the remote robotic avatar to approach the physical object at the remote second location and to initiate a teleoperative session between an entity in a first location and the remote robotic avatar at the remote second location.

Abstract: A computer-implemented method generates a hamming code based target label for each class of a dataset in which hamming distance between the target labels in the dataset is maximized and trains a convolutional neural network with the hamming codes based target label to thereby produce a trained AI model. The confusability between classes of the dataset is determined using a confusion matrix. The hamming distances of classes of the dataset that are determined to be more confusable are set to higher values than the hamming distances of classes of the dataset that are determined to be less confusable.

Abstract: A computer-implemented method comprises linking a private AI model to a public AI model to thereby form a combined AI model comprising the private AI model and the public AI model; and training the combined AI model with private samples while keeping the public AI model fixed so that only the private AI model is trained with the private samples.

Abstract: A method controls a remote robotic avatar based on a description of a physical object. A message transmitter transmits a message to a remote robotic avatar instructing the remote robotic avatar to identify a physical object at a second location, where an appearance of the physical object is described in the message. One or more processors determine a first position at the first location relative to the first object, also determine a second position at the second location that correlates with the first position by being a scaled distance away from the second object relative to the remote robotic avatar. The message transmitter transmits a message directing the remote robotic avatar to reposition itself to the second position at the second location, and to initiate a teleoperative session between the first person in the first location and the remote robotic avatar at the second location.

Abstract: A method controls a remote robotic avatar based on a description of a physical object. A message transmitter transmits a message to a remote robotic avatar instructing the remote robotic avatar to identify a physical object at a remote second location, where an appearance of the physical object is described in the message. The message transmitter also transmits an instruction to the remote robotic avatar to approach the physical object at the remote second location and to initiate a teleoperative session between an entity in a first location and the remote robotic avatar at the remote second location.

Abstract: A method controls a remote robotic avatar based on a description of a physical object. A message transmitter transmits a message to a remote robotic avatar instructing the remote robotic avatar to identify a physical object at a second location, where an appearance of the physical object is described in the message. One or more processors determine a first position at the first location relative to the first object, also determine a second position at the second location that correlates with the first position by being a scaled distance away from the second object relative to the remote robotic avatar. The message transmitter transmits a message directing the remote robotic avatar to reposition itself to the second position at the second location, and to initiate a teleoperative session between the first person in the first location and the remote robotic avatar at the second location.