Methods and systems for determining a network embedding include training a network embedding model using training data that includes topology information for networks and attribute information relating to vertices of the networks. An embedded representation is generated using the trained network embedding model to represent an input network, with associated attribute information, in a network topology space. A machine learning task is performed using the embedded representation as input to a machine learning model.

The present invention discloses a networked control system (NCS) time-delay compensation method based on predictive control. The method comprises the following steps: (1) acquiring random time-delay data in an NCS, and preprocessing the data; (2) predicting the current time-delay by using a fuzzy neural network (FNN) optimized by a particle swarm optimization (PSO) algorithm; (3) compensating the predicted time-delay by using an implicit proportional-integral-based generalized predictive control (PIGPC) algorithm; (4) determining whether a preset work end time is up according to a clock in the NCS; if yes, ending the process; if no, returning to step (2). The method disclosed by the present invention can accurately predict and effectively compensate the NCS time-delay and has excellent development prospect.

Systems and methods for parsing natural language sentences using an artificial neural network (ANN) are described. Embodiments of the described systems and methods may generate a plurality of word representation matrices for an input sentence, wherein each of the word representation matrices is based on an input matrix of word vectors, a query vector, a matrix of key vectors, and a matrix of value vectors, and wherein a number of the word representation matrices is based on a number of syntactic categories, compress each of the plurality of word representation matrices to produce a plurality of compressed word representation matrices, concatenate the plurality of compressed word representation matrices to produce an output matrix of word vectors, and identify at least one word from the input sentence corresponding to a syntactic category based on the output matrix of word vectors.

A computing system for generating a dynamic path for a fellow, includes a processor and a memory storing instructions that when executed by the processor cause the computing system to receive the fellow's skill graph, receive a target skill, receive a calendar object and generate the dynamic path including a task and/or a session. A non-transitory computer readable medium includes program instructions that when executed, cause a computer to receive the fellow's skill graph, receive a target skill, receive a calendar object and generate the dynamic path including a task and/or a session. A method for generating a dynamic path for a fellow includes receiving the fellow's skill graph, receiving a target skill, receiving a calendar object and generating the dynamic path including a task and/or a session.

Smart sensor methods and systems are described that improve on prior systems. An example device includes a sensor, a memory, a network connection, and two processing units, wherein a first processing unit compares current data provided by the first sensor to the reference data previously provided by the first sensor. Based on the result of the comparison, a second processing unit may be enabled to process the current data, or may be disabled to prevent the second processing unit from processing the current data.

Disclosed are an apparatus and method with neural processing. The operating method includes constructing a neuron array including a plurality of neuron modules, mapping a target pattern to the neuron array, adapting the neuron modules to the target pattern in response to a reception of the target pattern, and training the neuron modules to cause the neuron array to mimic the target pattern.

Described is a system and method for the classification of agents based on agent movement patterns. In operation, the system receives position data of a moving agent from a camera or sensor. Motion data of the moving agent is then extracted and used to generate a predicted future motion of the moving agent using a set of pre-calculated Echo State Networks (ESN). Each ESN represents an agent classification and generates a predicted future motion. A prediction error is generated for each ESN by comparing the predicted future motion for each ESN with actual motion data. Finally, the agent is classified based on the ESN having the smallest prediction error.

The present disclosure provides methods and systems for quantifying item performance in a digital shelf. A method for quantifying item performance in a digital shelf may comprise: calculating a value associated with a shelf share of the given item; determining a set of factors for calculating a score indicative of the item performance on the digital shelf, wherein the set of factors includes the shelf share; generating, using a trained machine learning algorithm, the score based on the set of factors; and displaying the score within a graphical user interface (GUI) on an electronic device.

Indications of sample machine learning models which create synthetic content items are provided via programmatic interfaces. A representation of a synthetic content item produced by one of the sample models in response to input obtained from a client of a provider network is presented. In response to a request from the client, a machine learning model is trained to produce additional synthetic content items.

Systems and methods disclosed are generally related to masklessly developing connections between a chip-group and a design connection point on a substrate. In placement of the chip-group on the substrate, according to certain embodiments the chip-group may be dispositioned relative to an expected position per a substrate layout design, causing a connection misalignment with the design connection point. According to certain embodiments, a machine learning (ML) model is trained on historical and simulated pixel models of chip-group connections and design connection points. Upon determining the chip-group misalignment by a metrology measurement, the trained ML model determines a pixel model to connect the misaligned chip-group, and causes the pixel model to be exposed to a substrate with a digital lithography tool, thereby connecting the dispositioned chip-group to the design connection point.