Abstract: A computer-implemented system and method includes establishing a station sequence that a given part traverses. Each station includes a machine that performs at least one operation with respect to the given part. Measurement data, which relates to attributes of a plurality of parts that traversed the plurality of machines, is received. The measurement data is obtained by sensors and corresponds to a current process period. A first machine learning model is pretrained to generate (i) latent representations based on the measurement data and (ii) machine states based on the latent representations. Machine observation data, which relates to the current process period, is received. Aggregated data is generated based on the measurement data and the machine observation data. A second machine learning model generates a maintenance prediction based on the aggregated data. The maintenance prediction corresponds to a next process period.

Abstract: A computer-implemented system and method include establishing a station sequence that a given part traverses. A history embedding sequence is generated and comprises (a) history measurement embeddings based on history measurement data, the history measurement data relating to attributes of at least one other part that traversed the plurality of stations before the given part, (b) history part identifier embeddings based at least one history part identifiers of at least one other part, and (c) history station identifier embeddings based on the at least one history station identifier corresponding to the history measurement data.

Abstract: A computer-implemented system and method includes establishing a station sequence that a given part traverses. A first neural network generates a set of parameter data based on observed measurement data of the given part at each station of a station subsequence. The set of parameter data is associated with a latent variable subsequence corresponding to the station subsequence. A second neural network generates next parameter data based on history measurement data and the set of parameter data. The history measurement data relates to another part processed before the given part and is associated with each station of the station sequence. The next parameter data is associated with a next latent variable that follows the latent variable subsequence. The next latent variable corresponds to a next station that follows the station subsequence in the station sequence.

Abstract: Methods and systems for classifying a article of manufacture are disclosed. A classifier is trained with training data including 1) a feature vector related to the article based on measurements related to the article captured at a particular station of a manufacturing process and 2) encoded time series data representing a history of measurements of articles of the same type as the article of manufacture captured at a sequence of stations of the manufacturing process prior to the particular station.

Abstract: A machine learning (ML) method for predicting an electronic structure of an atomic system. The method includes receiving an atomic identifier and an atomic position for atoms in the atomic system; receiving a basis set including rules for forming atomic orbitals of the atomic system; forming the atomic orbitals of the atomic system; and predicting an electronic structure of the atomic system based on the atom identifier, the atom position for the atoms in the atomic system, and the atomic orbitals of the atomic system. The ML method is capable of extremely accurate and fast molecular property prediction. The ML can directly purpose basis dependent information to predict molecular electronic structure. The ML method, which may be referred to as an orbital mixer model, uses multi-layer perception (MLP) mixer layers within a simple, intuitive, and scalable architecture to achieve competitive Hamiltonian and molecular orbital energy and coefficient prediction accuracies.

Abstract: A computer-implemented method includes applying a filter to input data based on an initial set of parameters to generate an initial feature map. The filter is configured to activate a filter function that involves a periodic function. The method includes performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform. The method includes applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map. The method includes performing a multiplicative operation on the first linear transform and the first feature map to generate a first product. The method includes performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform. The method includes generating output data that takes into account at least the second linear transform.

Abstract: Performing an adversarial attack on a neural network classifier is described. A dataset of input-output pairs is constructed, each input element of the input-output pairs randomly chosen from a search space, each output element of the input-output pairs indicating a prediction output of the neural network classifier for the corresponding input element. A Gaussian process is utilized on the dataset of input-output pairs to optimize an acquisition function to find a best perturbation input element from the dataset. The best perturbation input element is upsampled to generate an upsampled best input element. The upsampled best input element is added to an original input to generate a candidate input. The neural network classifier is queried to determine a classifier prediction for the candidate input. A score for the classifier prediction is computed. The candidate input is accepted as a successful adversarial attack responsive to the classifier prediction being incorrect.

Abstract: A computer-implemented method includes receiving a coarse mesh input that includes a first set of nodes, wherein the coarse mesh is input to a computational fluid dynamics solver with physical parameters to obtain a coarse mesh solution, receiving a fine mesh input that is of a second set of nodes, wherein the second set of nodes includes more nodes than the first set of nodes, concatenating the fine mesh input with the physical parameters and run the concatenation through a graph convolution layer to obtain a fine mesh hidden layer, upsampling the coarse mesh solution to obtain a coarse mesh upsample including a same number of nodes as the second set of nodes, and outputting a prediction in response to at least the coarse mesh upsample.

Abstract: A computer-implemented method includes applying a filter to input data based on an initial set of parameters to generate an initial feature map. The filter is configured to activate a filter function that involves a periodic function. The method includes performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform. The method includes applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map. The method includes performing a multiplicative operation on the first linear transform and the first feature map to generate a first product. The method includes performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform. The method includes generating output data that takes into account at least the second linear transform.

Abstract: A computer-implemented method includes receiving a coarse mesh input that includes a first set of nodes, wherein the coarse mesh is input to a computational fluid dynamics solver with physical parameters to obtain a coarse mesh solution, receiving a fine mesh input that is of a second set of nodes, wherein the second set of nodes includes more nodes than the first set of nodes, concatenating the fine mesh input with the physical parameters and run the concatenation through a graph convolution layer to obtain a fine mesh hidden layer, upsampling the coarse mesh solution to obtain a coarse mesh upsample including a same number of nodes as the second set of nodes, and outputting a prediction in response to at least the coarse mesh upsample.

Abstract: A simulation includes converting a molecular dynamics snapshot of elements within a multi-element system into a graph with atoms as nodes of the graph; defining a matrix such that each column of the matrix represents a node in the graph; defining a distance matrix according to a set of relative positions of each of the atoms; iterating through the GTFF using an attention mechanism, operating on the matrix and augmented by incorporating the distance matrix, to pass hidden state from a current layer of the GTFF to a next layer of the GTFF; performing a combination over the columns of the matrix to produce a scalar molecular energy; making a backward pass through the GTFF, iteratively calculating derivatives at each of the layers of the GTFF to compute a prediction of force acting on each atom; and returning the prediction of the force acting on each atom.

Abstract: Performing an adversarial attack on a neural network classifier is described. A dataset of input-output pairs is constructed, each input element of the input-output pairs randomly chosen from a search space, each output element of the input-output pairs indicating a prediction output of the neural network classifier for the corresponding input element. A Gaussian process is utilized on the dataset of input-output pairs to optimize an acquisition function to find a best perturbation input element from the dataset. The best perturbation input element is upsampled to generate an upsampled best input element. The upsampled best input element is added to an original input to generate a candidate input. The neural network classifier is queried to determine a classifier prediction for the candidate input. A score for the classifier prediction is computed. The candidate input is accepted as a successful adversarial attack responsive to the classifier prediction being incorrect.

Abstract: A simulation includes converting a molecular dynamics snapshot of elements within a multi-element system into a graph with atoms as nodes of the graph; defining a matrix such that each column of the matrix represents a node in the graph; defining a distance matrix according to a set of relative positions of each of the atoms; iterating through the GTFF using an attention mechanism, operating on the matrix and augmented by incorporating the distance matrix, to pass hidden state from a current layer of the GTFF to a next layer of the GTFF; performing a combination over the columns of the matrix to produce a scalar molecular energy; making a backward pass through the GTFF, iteratively calculating derivatives at each of the layers of the GTFF to compute a prediction of force acting on each atom; and returning the prediction of the force acting on each atom.