Abstract: Techniques for generating and managing, including simulating and training, deep tensor neural networks are presented. A deep tensor neural network comprises a graph of nodes connected via weighted edges. A network management component (NMC) extracts features from tensor-formatted input data based on tensor-formatted parameters. NMC evolves tensor-formatted input data based on a defined tensor-tensor layer evolution rule, the network generating output data based on evolution of the tensor-formatted input data. The network is activated by non-linear activation functions, wherein the weighted edges and non-linear activation functions operate, based on tensor-tensor functions, to evolve tensor-formatted input data. NMC trains the network based on tensor-formatted training data, comparing output training data output from the network to simulated output data, based on a defined loss function, to determine an update.

Abstract: Techniques for generating and managing, including simulating and training, deep tensor neural networks are presented. A deep tensor neural network comprises a graph of nodes connected via weighted edges. A network management component (NMC) extracts features from tensor-formatted input data based on tensor-formatted parameters. NMC evolves tensor-formatted input data based on a defined tensor-tensor layer evolution rule, the network generating output data based on evolution of the tensor-formatted input data. The network is activated by non-linear activation functions, wherein the weighted edges and non-linear activation functions operate, based on tensor-tensor functions, to evolve tensor-formatted input data. NMC trains the network based on tensor-formatted training data, comparing output training data output from the network to simulated output data, based on a defined loss function, to determine an update.

Abstract: Techniques for generating and managing, including simulating and training, deep tensor neural networks are presented. A deep tensor neural network comprises a graph of nodes connected via weighted edges. A network management component (NMC) extracts features from tensor-formatted input data based on tensor-formatted parameters. NMC evolves tensor-formatted input data based on a defined tensor-tensor layer evolution rule, the network generating output data based on evolution of the tensor-formatted input data. The network is activated by non-linear activation functions, wherein the weighted edges and non-linear activation functions operate, based on tensor-tensor functions, to evolve tensor-formatted input data. NMC trains the network based on tensor-formatted training data, comparing output training data output from the network to simulated output data, based on a defined loss function, to determine an update.

Abstract: A tensor decomposition method, system, and computer program product include compressing multi-dimensional data by truncated tensor-tensor decompositions.

Abstract: A tensor decomposition method, system, and computer program product include compressing multi-dimensional data by truncated tensor-tensor decompositions.

Abstract: Techniques for generating and managing, including simulating and training, deep tensor neural networks are presented. A deep tensor neural network comprises a graph of nodes connected via weighted edges. A network management component (NMC) extracts features from tensor-formatted input data based on tensor-formatted parameters. NMC evolves tensor-formatted input data based on a defined tensor-tensor layer evolution rule, the network generating output data based on evolution of the tensor-formatted input data. The network is activated by non-linear activation functions, wherein the weighted edges and non-linear activation functions operate, based on tensor-tensor functions, to evolve tensor-formatted input data. NMC trains the network based on tensor-formatted training data, comparing output training data output from the network to simulated output data, based on a defined loss function, to determine an update.

Abstract: A system for behavioral monitoring for equines, comprising at least one sensor to measure a signal related to the equine, a database to store at least one parameter of the equine as a function of time, and processing means. The sensor is in communication with the equine, and comprises a wireless transmitter which is in communication with the database. The processing means, in communication with the database, is adapted to (i) determine, from at least one signal from the at least one sensor, at least one parameter of the equine as a function of time; (ii) establish normal behavior of the equine based on the parameter; and (iii) identify at least one abnormal behavior of the equine by identifying at least one deviation from normal behavior.

Abstract: A system for behavioral monitoring for equines, comprising at least one sensor to measure a signal related to the equine, a database to store at least one parameter of the equine as a function of time, and processing means. The sensor is in communication with the equine, and comprises a wireless transmitter which is in communication with the data-base. The processing means, in communication with the database, is adapted to (i) determine, from at least one signal from the at least one sensor, at least one parameter of the equine as a function of time; (ii) establish normal behavior of the equine based on the parameter; and (iii) identify at least one abnormal behavior of the equine by identifying at least one deviation from normal behavior.