Abstract: Provided is a system for detecting an anomaly in a multivariate time series that includes at least one processor programmed or configured to receive a dataset of a plurality of data instances, wherein each data instance comprises a time series of data points, determine a set of target data instances based on the dataset, determine a set of historical data instances based on the dataset, generate, based on the set of target data instances, a true value matrix, a true frequency matrix, and a true correlation matrix, generate a forecast value matrix, a forecast frequency matrix, and a forecast correlation matrix based on the set of target data instances and the set of historical data instances, determine an amount of forecasting error, and determine whether the amount of forecasting error corresponds to an anomalous event associated with the dataset of data instances. Methods and computer program products are also provided.

Abstract: A method includes receiving a first data set comprising embeddings of first and second types, generating a fixed adjacency matrix from the first dataset, and applying a first stochastic binary mask to the fixed adjacency matrix to obtain a first subgraph of the fixed adjacency matrix. The method also includes processing the first subgraph through a first layer of a graph convolutional network (GCN) to obtain a first embedding matrix, and applying a second stochastic binary mask to the fixed adjacency matrix to obtain a second subgraph of the fixed adjacency matrix. The method includes processing the first embedding matrix and the second subgraph through a second layer of the GCN to obtain a second embedding matrix, and then determining a plurality of gradients of a loss function, and modifying the first stochastic binary mask and the second stochastic binary mask using at least one of the plurality of gradients.

Abstract: A method (1000) for performance modeling of a plurality of microservices (215) includes deploying the plurality of microservices (215) within a network (1260). The plurality of microservices (215) are communicatively coupled to generate at least one service chain (310) for providing at least one service. Based on a resource allocation configuration, an initial set of training data for the plurality of microservices within the network (1260) is determined. At least a portion of data is excluded from the initial set of training data to generate a subset of training data. A Quality of Service (QoS) behaviour model is generated based on the subset of the training data.

Abstract: A database management system receives a command defining a view of the database. The view definition is accepted without determining whether references to schema elements within the view definition are resolvable to existing elements of the database schema. A query of the view is received. In response to the query of the view, the database management system resolves references to schema elements in the view definition by determining whether the references correspond to data available for processing the query.

Abstract: Described are a method, system, and computer program product for generating robust graph neural networks using universal adversarial training. The method includes receiving a graph neural network (GNN) model and a bipartite graph including an adjacency matrix, initializing model parameters of the GNN model, initializing perturbation parameters, and sampling a subgraph of a complementary graph based on the bipartite graph. The method further includes repeating until convergence of the model parameters: drawing a random variable from a uniform distribution; generating a universal perturbation matrix based on the subgraph, the random variable, and the perturbation parameters; determining Bayesian Personalized Ranking (BPR) loss by inputting the bipartite graph and the universal perturbation matrix to the GNN model; updating the perturbation parameters based on stochastic gradient ascent; and updating the model parameters based on stochastic gradient descent.

Abstract: Methods for forming defect-free gap fill materials comprising germanium oxide are disclosed. In some embodiments, the gap fill material is deposited by exposing a substrate surface to a germane precursor and an oxidant simultaneously. The germane precursor may be flowed intermittently. The substrate may also be exposed to a second oxidant to increase the relative concentration of oxygen within the gap fill material. A process for removal of germanium oxide is also disclosed.

Abstract: Exemplary methods of semiconductor processing may include providing a silicon-containing precursor to a processing region of a semiconductor processing chamber. A substrate may be disposed within the processing region of the semiconductor processing chamber. The methods may include depositing a silicon-containing material on the substrate. Subsequent a first period of time, the methods may include providing a germanium-containing precursor to the processing region of the semiconductor processing chamber. The methods may include thermally reacting the silicon-containing precursor and the germanium-containing precursor at a temperature greater than or about 400° C. The methods may include forming a silicon-and-germanium-containing layer on the substrate.

Abstract: Examples of the present technology include semiconductor processing methods to form diffusion barriers for germanium in a semiconductor structure. The methods may include forming a semiconductor layer stack from pairs of Si-and-SiGe layers. The Si-and-SiGe layer pairs may be formed by forming a silicon layer, and then forming the germanium barrier layer of the silicon layer. In some embodiments, the germanium-barrier layer may be less than or about 20 ?. A silicon-germanium layer may be formed on the germanium-barrier layer to complete the formation of the Si-and-SiGe layer pair. In some embodiments, the silicon layer may be an amorphous silicon layer, and the SiGe layer may be characterized by greater than or about 5 atom % germanium. Examples of the present technology also include semiconductor structures that include a silicon-germanium layer, a germanium-barrier layer, and a silicon layer.

Abstract: Methods for forming defect-free gap fill materials comprising germanium oxide are disclosed. In some embodiments, the gap fill material is deposited by exposing a substrate surface to a germane precursor and an oxidant simultaneously. The germane precursor may be flowed intermittently. The substrate may also be exposed to a second oxidant to increase the relative concentration of oxygen within the gap fill material.

Abstract: A non-conformal, highly selective liner for etch methods in semiconductor devices is described. A method comprises forming a film stack on a substrate; etching the film stack to form an opening; depositing a non-conformal liner in the opening; etching the non-conformal liner from the bottom of the opening; and selectively etching the film stack relative to the non-conformal liner to form a logic or memory hole. The non-conformal liner comprises one or more of boron, carbon, or nitrogen.

Abstract: A method (1000) for performance modeling of a plurality of microservices (215) includes deploying the plurality of microservices (215) within a network (1260). The plurality of microservices (215) are communicatively coupled to generate at least one service chain (310) for providing at least one service. Based on a resource allocation configuration, an initial set of training data for the plurality of microservices within the network (1260) is determined. At least a portion of data is excluded from the initial set of training data to generate a subset of training data. A Quality of Service (QoS) behaviour model is generated based on the subset of the training data.

Abstract: Methods of etching film stacks to form gaps of uniform width are described. A film stack is etched through a hardmask. A conformal liner is deposited in the gap. The bottom of the liner is removed. The film stack is selectively etched relative to the liner. The liner is removed. The method may be repeated to a predetermined depth.

Abstract: Exemplary methods of semiconductor processing may include providing a silicon-containing precursor to a processing region of a semiconductor processing chamber. A substrate may be disposed within the processing region of the semiconductor processing chamber. The methods may include depositing a silicon-containing material on the substrate. Subsequent a first period of time, the methods may include providing a germanium-containing precursor to the processing region of the semiconductor processing chamber. The methods may include thermally reacting the silicon-containing precursor and the germanium-containing precursor at a temperature greater than or about 400° C. The methods may include forming a silicon-and-germanium-containing layer on the substrate.

Abstract: Examples of the present technology include semiconductor processing methods to form boron-containing materials on substrates. Exemplary processing methods may include delivering a deposition precursor that includes a boron-containing precursor to a processing region of a semiconductor processing chamber. A plasma may be formed from the deposition precursor within the processing region of the semiconductor processing chamber. The methods may further include depositing a boron-containing material on a substrate disposed within the processing region of the semiconductor processing chamber, where the substrate is characterized by a temperature of less than or about 50° C. The as-deposited boron-containing material may be characterized by a surface roughness of less than or about 2 nm, and a stress level of less-than or about ?500 MPa. In some embodiments, a layer of the boron-containing material may function as a hardmask.

Abstract: Examples of the present technology include semiconductor processing methods that provide a substrate in a substrate processing region of a substrate processing chamber, where the substrate is maintained at a temperature less than or about 50° C. A plasma may be generated from the hydrocarbon-containing precursor, and a carbon-containing material may be deposited from the plasma on the substrate. The carbon-containing material may include diamond-like-carbon, and may have greater than or about 60% of the carbon atoms with sp3 hybridized bonds.

Abstract: Examples of the present technology include semiconductor processing methods that provide a substrate in a substrate processing region of a substrate processing chamber, where the substrate is maintained at a temperature less than or about 50° C. An inert precursor and a hydrocarbon-containing precursor may be flowed into the substrate processing region of the substrate processing chamber, where a flow rate ratio of the inert precursor to the hydrocarbon-containing precursor may be greater than or about 10:1. A plasma may be generated from the inert precursor and the hydrocarbon-containing precursor, and a carbon-containing material may be deposited from the plasma on the substrate. The carbon-containing material may include diamond-like-carbon, and may have greater than or about 60% of the carbon atoms with sp3 hybridized bonds.

Abstract: Methods for forming defect-free gap fill materials comprising germanium oxide are disclosed. In some embodiments, the gap fill material is deposited by exposing a substrate surface to a germane precursor and an oxidant simultaneously. The germane precursor may be flowed intermittently. The substrate may also be exposed to a second oxidant to increase the relative concentration of oxygen within the gap fill material.

Abstract: Methods for forming coating films comprising germanium oxide are disclosed. In some embodiments, the films are super-conformal to a feature on the surface of a substrate. The films are deposited by exposing a substrate surface to a germane precursor and an oxidant simultaneously. The germane precursor may be flowed intermittently. The substrate may also be exposed to a second oxidant to increase the relative concentration of oxygen within the super-conformal film.

Abstract: Methods for depositing a silicon-germanium film on a substrate are described. The method comprises exposing a substrate to a silicon precursor and a germanium precursor to form a conformal silicon-germanium film. The substrate comprises at least one film stack and at least one feature, the film stack comprising alternating layers of silicon and silicon-germanium. The silicon-germanium film has a conformality greater than 50%.

Abstract: Methods for selectively depositing germanium containing films are disclosed. Some embodiments of the disclosure provide deposition on a bare silicon with little to no deposition on a silicon oxide surface. Some embodiments of the disclosure provide conformal films on trench sidewalls. Some embodiments of the disclosure provide superior gap fill without seams or voids.