Methods and systems for explainable machine learning are described. In an example, a processor can receive a data set from a plurality of data sources corresponding to a plurality of domains. The processor can train a machine learning model to learn a plurality of vectors that indicate impact of the plurality of domains on a plurality of assets. The machine learning model can be operable to generate forecasts relating to performance metrics of the plurality of assets based on the plurality of vectors. In some examples, the machine learning model can be a neural attention network with shared hidden layers.

A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism. The application of structured sparsity lowers the span of search options and creates a relatively loose coupling between the data and control planes.

A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism. The application of structured sparsity lowers the span of search options and creates a relatively loose coupling between the data and control planes.

Techniques facilitating generation of a fused kernel that can approximate a full kernel of a convolutional neural network are provided. In one example, a computer-implemented method comprises determining a first pattern of samples of a first sample matrix and a second pattern of samples of a second sample matrix. The first sample matrix can be representative of a sparse kernel, and the second sample matrix can be representative of a complementary kernel. The first pattern and second pattern can be complementary to one another. The computer-implemented method also comprises generating a fused kernel based on a combination of features of the sparse kernel and features of the complementary kernel that are combined according to a fusing approach and training the fused kernel.

A method to process data. A plurality of data points or a representation of a plurality of data points is created combining the data traversing processing units of the system with other data accessible to the system (including data from its memories, interfaces and processing units), and an operation of compression or of pattern recognition is applied to the output of the previous operation.

Systems, Apparatuses and Methods for implementing a neural network system for controlling an autonomous vehicle (AV) are provided, which includes: a neural network having a plurality of nodes with context to vector (context2vec) contextual embeddings to enable operations of the AV; a plurality of encoded context2vec AV words in a sequence of timing to embed data of context and behavior; a set of inputs which comprise: at least one of a current, a prior, and a subsequent encoded context2vec AV word; a neural network solution applied by the at least one computer to determine a target context2vec AV word of each set of the inputs based on the current context2vec AV word; an output vector computed by the neural network that represents the embedded distributional one-hot scheme of the input encoded context2vec AV word; and a set of behavior control operations for controlling a behavior of the AV.

A method for acoustic source separation comprises inputting acoustic data from a plurality of acoustic sensors, combined from a plurality of acoustic sources, converting the acoustic data to time-frequency domain data comprising time-frequency data frames, and constructing a multichannel filter for the time-frequency data frames to separate signals from the acoustic sources. The constructing comprises determining a set of de-mixing matrices (W.sub.f) to apply to each time-frequency data frame to determine a vector of separated outputs (y.sub.ft) by modifying each of the de-mixing matrices by a respective gradient value (G;G) for a frequency dependent upon a gradient of a cost function measuring a separation of the sources by the respective de-mixing matrix. The respective gradient values for each frequency are each calculated from a stochastic selection of the time-frequency data frames.

Using a plurality of distinct behavioral tasks conducted in a functional magnetic resonance imaging (fMRI) scanner, fMRI data acquired from one or more subjects performing working memory tasks can be used for diagnosing psychiatrics and neurological disorders. A classification algorithm can be used to determine a classification model, tune the model, and apply the model. An output indicative of a subject's clinical condition can then be provided and used to diagnose new cases.

Systems, Apparatuses and Methods for implementing a neural network system for controlling an autonomous vehicle (AV) are provided, which includes: a neural network having a plurality of nodes with context to vector (context2vec) contextual embeddings to enable operations of the of the AV; a plurality of encoded context2vec AV words in a sequence of timing to embed data of context and behavior; a set of inputs which comprise: at least one of a current, a prior, and a subsequent encoded context2vec AV word; a neural network solution applied by the at least one computer to determine a target context2vec AV word of each set of the inputs based on the current context2vec AV word; an output vector computed by the neural network that represents the embedded distributional one-hot scheme of the input encoded context2vec AV word; and a set of behavior control operations for controlling a behavior of the AV.

A method for determining a vehicle system prognosis includes detecting a predetermined characteristic of a vehicle with one or more sensors, receiving a plurality of sensor signals from the one or more sensors and determining an input time series of data based on the sensor signals, clustering a matrix of time series data, generated from the input time series of data, into a predetermined number of hyperplanes, extracting extracted features that are indicative of an operation of a vehicle system from a sparse temporal matrix based on data point behavior with respect to two or more hyperplanes within the sparse temporal matrix and determining an operational status of the vehicle system based on the extracted features, the sparse temporal matrix being based on the predetermined number of hyperplanes; and communicating the operational status of the vehicle system to an operator or crew member of the vehicle.