Abstract: A key updater for a first party operating on a network generates a mutually distilled key for communication between the first party and a second party. The key updater determines a set of verifying parties operating on the network needed to authenticate the mutually distilled key, wherein each verifying party of the set of verifying parties operates on the network. The key updater iteratively executes a key equivalency test for each verifying party in the set of verifying parties to determine a nonce sum until the key equivalency test has been executed for each of the verifying parties in the set of verifying parties or until it is determined that at least one node on the network has been compromised. The key updater generates a final key for communication between the first party and the second party based on the nonce sum and the mutually distilled key.

Abstract: A key updater for a first party operating on a network generates a mutually distilled key for communication between the first party and a second party. The key updater determines a set of verifying parties operating on the network needed to authenticate the mutually distilled key, wherein each verifying party of the set of verifying parties operates on the network. The key updater iteratively executes a key equivalency test for each verifying party in the set of verifying parties to determine a nonce sum until the key equivalency test has been executed for each of the verifying parties in the set of verifying parties or until it is determined that at least one node on the network has been compromised. The key updater generates a final key for communication between the first party and the second party based on the nonce sum and the mutually distilled key.

Abstract: A method for selecting a final model for detecting cells of interest in image datasets includes dividing a curated image dataset into a training set, a validation set, and a testing set where each image in the curated image dataset has been labeled as positive or negative for a cell of interest. The method trains each model of an ensemble of neural networks using the training and validation sets. Next, each model of the ensemble is tested using the testing set and the predictions of the ensemble are combined. The combined prediction is compared to the label and the method determines whether the combined prediction satisfies a pre-determined level of detection (LOD). If so, the method outputs the ensemble as a final ensemble. If not, the method modifies a hyperparameter of at least one of the models of the ensemble until the combined prediction satisfies the pre-determined LOD.

Abstract: A method for a dealer to manage products in an inventory includes providing an interface and a processor. The interface is connected for communication with the processor. The interface and the processor are configured so the dealer can provide a plurality of rules through the interface for running on the processor. The processor is configured for running a program for applying the rules to input information that may be provided to the processor regarding a product in the inventory. Outputs of the running the program applying the rules include at least one merchandising action regarding a product in the inventory. The processor is connected to automatically receive the input information and the processor is configured for running a program to automatically implement the at least one merchandising action resulting from applying the rules to the input information.