Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: A method for measuring relatedness between prediction tasks includes receiving data for a first prediction task. The method further includes measuring the relatedness of the first prediction task to at least one previous prediction task as a difference between divergence of conditional probabilities of the tasks. The method can be advantageously applied in artificial intelligence or continual learning systems.

Abstract: A method for scalable multi-task learning with convex clustering includes: extracting features from a dataset of a plurality of tasks; generating a graph from the extracted features, nodes of the graph representing linear learning models, each of the linear learning models being for one of the tasks; constraining the graph using convex clustering to generate a convex cluster constrained graph; and obtaining a global solution by minimizing a graph variable loss function, the minimizing the graph variable loss function comprising: introducing auxiliary variables for each connection between nodes in the convex cluster constrained graph; iteratively performing the following operations until convergence: updating the linear learning models by solving a sparse linear system; and updating the auxiliary variables by solving an equation having the auxiliary variables each be proportional to a vector norm for their respective nodes.

Abstract: A method for affinity graph extraction includes building an affinity graph based on data, the data including multiple elements with undetermined relationships, wherein each element is represented as a node in the affinity graph and relations between nodes are represented as edges in the affinity graph. The method further includes applying a machine learning algorithm to learn node and relation representations in the affinity graph, wherein each edge has a relation type selected from a set of two or more relation types, learning a machine learning scoring function for each relation type, and adjusting the affinity graph based on the scoring function and iteratively repeating operations of applying, learning and adjusting one or more times to determine new relations between nodes representing the undetermined relationships.

Abstract: A method of continual learning in an artificial intelligence system through bi-level optimization includes providing a stored data sample of a current task and providing a neural network subdivided into two parts including a parameter part and a hyper-parameter part. The method further includes performing bi-level optimization by separately training the two parts of the neural network. The neural network has been trained, prior to the bi-level optimization, on data samples of previous tasks.

Abstract: A method for online learning from a data stream with an ensemble of meta-trees includes: observing a data instance from the data stream; for each of the meta-trees, replicating the data instance to generate a number of replicated data instances; for each of the meta-trees, updating meta-tree components using the number or replicated data instances; and inducing each of the meta-trees based on the data instance and the updated meta-tree components. Inducing each of the meta-trees includes employing inequality concentration bound to determine whether a split criterion is satisfied.

Abstract: A method for modular-based techniques for continual learning applications includes training a neural network based on learning a plurality of parameters associated with the neural network using input data associated with a current task. The neural network comprises a plurality of layers. A first layer, of the plurality of layers, comprises a plurality of nodes. Modularization of the neural network is performed to group the plurality of nodes of the first layer into at least two separate groups.

Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: A method for measuring relatedness between prediction tasks includes receiving data for a first prediction task. The method further includes measuring the relatedness of the first prediction task to at least one previous prediction task as a difference between divergence of conditional probabilities of the tasks. The method can be advantageously applied in artificial intelligence or continual learning systems.

Abstract: A method of continual learning in an artificial intelligence system through bi-level optimization includes providing a stored data sample of a current task and providing a neural network subdivided into two parts including a parameter part and a hyper-parameter part. The method further includes performing bi-level optimization by separately training the two parts of the neural network. The neural network has been trained, prior to the bi-level optimization, on data samples of previous tasks.

Abstract: Systems and methods for simultaneously displaying an external visual cue received at a primary display device on one or more secondary display devices in a distributed presentation system. The method includes displaying original content on a primary display device, detecting an external visual cue on the displayed original content, determining one or more parameters of the external visual cue, the one or more parameters including at least a location of the external visual cue relative to, or on, the displayed original content, and communicating the one or more parameters to one or more secondary display devices that are displaying the original content, to enable the one or more secondary display devices to display a representation of the external visual cue simultaneously with displaying the original content.

Abstract: A method for online learning from a data stream with an ensemble of meta-trees includes: observing a data instance from the data stream; for each of the meta-trees, replicating the data instance to generate a number of replicated data instances; for each of the meta-trees, updating meta-tree components using the number or replicated data instances; and inducing each of the meta-trees based on the data instance and the updated meta-tree components. Inducing each of the meta-trees includes employing inequality concentration bound to determine whether a split criterion is satisfied.

Abstract: A method for scalable multi-task learning with convex clustering includes: extracting features from a dataset of a plurality of tasks; generating a graph from the extracted features, nodes of the graph representing linear learning models, each of the linear learning models being for one of the tasks; constraining the graph using convex clustering to generate a convex cluster constrained graph; and obtaining a global solution by minimizing a graph variable loss function, the minimizing the graph variable loss function comprising: introducing auxiliary variables for each connection between nodes in the convex cluster constrained graph; iteratively performing the following operations until convergence: updating the linear learning models by solving a sparse linear system; and updating the auxiliary variables by solving an equation having the auxiliary variables each be proportional to a vector norm for their respective nodes.