Abstract: The present disclosure relates to systems and methods for optimizing neural networks by strategically identifying and pruning critical neurons to reduce computational resources while maintaining high levels of accuracy. The method involves determining critical neurons within a neural network based on features collected during an initial phase of training. These critical neurons are then pruned from the network, resulting in a pruned neural network with the critical neurons removed. The training process continues using the pruned neural network, allowing for significant computational savings without substantially impacting the network's performance.

Abstract: A method and system for polymorphic pruning of neural networks are disclosed. The method involves training a neural network model on an input dataset for an initial predetermined number of iterations to gather weight information, including the strength of each weight and changes in strength over iterations. The weights are stored in an array accessible to a pruning algorithm. An objective function is compiled using the weight information, and an optimization tool solves the objective function to generate a solution vector. This solution vector is used to create a pruning mask, which is applied to the neural network model to prune certain weights by setting them to zero. The pruned weight vector updates the model, resulting in a neural network with fewer non-zero connections between neurons.

Abstract: A computer-implemented method for optimizing neural networks by detecting critical and non-critical nodes is disclosed. The method involves obtaining a neural network comprising a plurality of nodes and their weighted connections. Critical nodes, which have a greater correlation to the network's output than non-critical nodes, are identified through a two-step detection process. The first critical node detection process identifies critical nodes based on weighted direct connections among the nodes. The second critical node detection process identifies critical nodes based on unweighted direct and indirect connections. The configuration of the neural network is then adjusted based on the identified critical and non-critical nodes to improve efficiency or reduce size.

Abstract: An investment portfolio is determined by converting historical information about available investments and investment objectives into a probabilistic objective function, converting the probabilistic objective function into a quadratic unconstrained binary optimization (QUBO) problem, solving the QUBO problem with a quantum or quantum-inspired computer, and converting the optimized QUBO variables into real variables to determine an optimum distribution of funds.

Abstract: A computer method and system for optimizing distribution of supply items from a plurality of inventory locations to a plurality of demand locations includes, with a server computer, obtaining inventory and demand data and establishing a quadratic unconstrained binary optimization (QUBO) problem corresponding to the distribution. Data corresponding to the QUBO problem is transferred to a quantum computer for solution. The QUBO solution is converted, by the server computer, to instructions corresponding to optimized item transfer, and displaying the instructions on electronic displays of networked devices. Computer methods may include selecting a solver computer program appropriate for problem complexity. Computer methods may include selecting a quantum computer, quantum-inspired computer, or computer array appropriate for solution.

Abstract: Systems and methods are described for automated anomaly detection. For example, the system receives various types of unlabeled data and determines, through an unsupervised machine learning model, a label for the data. The labels are provided to a supervised machine learning model during a first training process. The system also performs unsupervised labeling and supervised labeling of network flows to infer anomalous network traffic. When new data is received, the supervised machine learning model is executed during an inference process to cluster the new data in accordance with the labels that were determined by the unsupervised machine learning model. In some examples, the system may combine the unsupervised machine learning model with a supervised machine learning model to perform automated anomaly detection.

Abstract: Systems and methods are described for automated threat detection. For example, the system receives labels that are generated by an unsupervised machine learning model. Using the labels, the system initiates a training process of a supervised machine learning model using the set of labels from the unsupervised machine learning model. The supervised machine learning model can generate a set of clustered data during an inference process. The supervised machine learning model can be updated and stored in a model data store for future inference processes on new data.

Abstract: Systems and methods are described for automated threat detection. For example, the system receives various types of unlabeled data and determines, through an unsupervised machine learning model, a label for the data. The labels are provided to a supervised machine learning model during a first training process. When new data is received, the supervised machine learning model is executed during an inference process to cluster the new data in accordance with the labels that were determined by the unsupervised machine learning model. In some examples, a label audit process may be implemented to update the cluster/output of the supervised machine learning model. The updated labels from the label audit process may be provided back to the supervised machine learning model during a second training process. In other words, the system may combine the unsupervised machine learning model with a supervised machine learning model to perform automated threat detection.