Nec Corporation

Xiao He

Ammar Shaker

Francesco Alesiani

Luis Moreira-Matias

Christoph Gaertner

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.

Method and system for scalable multi-task learning with convex clustering

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.

Continual learning of artificial intelligence systems based on bi-level optimization

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.

Method and system for adaptive online meta learning from data streams

A method for processing an input data matrix so as to provide co-clustering assignments of rows and columns of the input data matrix includes generating, from the input data matrix, a graph of rows in the data matrix and a graph of columns in the data matrix, determining an objective function for generating a compact representation of the input data matrix, and generating the compact representation of the input data matrix by performing alternating optimization of the objective function until a test compact representation that causes the objective function to converge is generated. The method additionally includes generating a new graph of rows and a new graph of columns from the compact representation of the input data matrix, and returning a connected component of the new graph of rows and a connected component of the new graph of columns as the co-clustering assignments of the rows and columns.

Growing community of inventors

Heidelberg, Germany

Xiao He