Abstract: A system makes predictions using a machine learning model combined with a knowledge model. The system provides input data to a knowledge model and a machine learning based model. The machine learning based model is trained to make predictions based on input data. The system provides the outputs of the machine learning based model and the knowledge model to an ensemble model configured to combine results of the knowledge model and the machine learning based model. The system can be used for several applications. For example, the system may classify an input text based on a hierarchy of categories. The system may perform fault detection in time series data by identifying an anomaly data point and predicting whether the anomaly data point is a fault.

Abstract: A system makes predictions using a machine learning model combined with a knowledge model. The system provides input data to a knowledge model and a machine learning based model. The machine learning based model is trained to make predictions based on input data. The system provides the outputs of the machine learning based model and the knowledge model to an ensemble model configured to combine results of the knowledge model and the machine learning based model. The system can be used for several applications. For example, the system may classify an input text based on a hierarchy of categories. The system may perform fault detection in time series data by identifying an anomaly data point and predicting whether the anomaly data point is a fault.

Abstract: A system makes predictions using a machine learning model combined with a knowledge model. The system provides input data to a knowledge model and a machine learning based model. The machine learning based model is trained to make predictions based on input data. The system provides the outputs of the machine learning based model and the knowledge model to an ensemble model configured to combine results of the knowledge model and the machine learning based model. The system can be used for several applications. For example, the system may classify an input text based on a hierarchy of categories. The system may perform fault detection in time series data by identifying an anomaly data point and predicting whether the anomaly data point is a fault.

Abstract: A predictive maintenance server receives data from sensors of equipment. The server uses one or more machine learning models to assign an anomaly score. Responsive to the anomaly score exceeding a threshold value, the server may issue an alert. The machine learning model may be supervised or unsupervised. In one embodiment, the machine learning model use several sensor channels to predict the values of one or more vitals of the equipment and compare the predicted values to the actual measured values of the vitals. The server may assign an anomaly score based on the differences between the predicted values and the measured values. In one embodiment, the machine learning model may be an autoencoder that generates a distribution of the measurement values to determine the likelihood of observing the actual measured values in a normal operation. In one embodiment, the server may use a histogram approach to predict anomaly.

Abstract: A predictive maintenance server receives data from sensors of equipment. The server uses one or more machine learning models to assign an anomaly score. Responsive to the anomaly score exceeding a threshold value, the server may issue an alert. The machine learning model may be supervised or unsupervised. In one embodiment, the machine learning model use several sensor channels to predict the values of one or more vitals of the equipment and compare the predicted values to the actual measured values of the vitals. The server may assign an anomaly score based on the differences between the predicted values and the measured values. In one embodiment, the machine learning model may be an autoencoder that generates a distribution of the measurement values to determine the likelihood of observing the actual measured values in a normal operation. In one embodiment, the server may use a histogram approach to predict anomaly.

Abstract: Embodiments of systems and methods for patterning features in tantalum nitride (TaN) are described. In an embodiment, a method may include receiving a substrate comprising a TaN layer. The method may also include etching the substrate to expose at least a portion of the TaN layer. Additionally, the method may include performing a passivation process to reduce lateral etching of the TaN layer. The method may further include etching the TaN layer to form a feature therein, wherein the passivation process is controlled to meet one or more target passivation objectives.

Abstract: Provided is a method of forming a spacer sidewall mask, the method comprising: providing a substrate in a process chamber, the substrate having a carbon mandrel pattern and an underlying layer, the underlying layer comprising an amorphous silicon layer above a silicon nitride layer; performing a breakthrough etch process including growth of a conformal native silicon oxide layer, creating an ALD patterned structure; performing a spacer sidewall sculpting process on the ALD patterned structure; performing an amorphous silicon main etch (ME) process on the ALD patterned structure, the ME process causing a spacer oxide open and carbon mandrel removal; and performing an amorphous silicon ME over etch (OE) process on the ALD spacer oxide pattern, the ME OE process transferring the ALD spacer oxide pattern into the amorphous silicon layer, generating a first sculpted pattern comprising a first sculpted sub-structure with a trapezoidal shape.

Abstract: Embodiments of systems and methods for patterning features in tantalum nitride (TaN) are described. In an embodiment, a method may include receiving a substrate comprising a TaN layer. The method may also include etching the substrate to expose at least a portion of the TaN layer. Additionally, the method may include performing a passivation process to reduce lateral etching of the TaN layer. The method may further include etching the TaN layer to form a feature therein, wherein the passivation process is controlled to meet one or more target passivation objectives.

Abstract: Provided is a method of forming a spacer sidewall mask, the method comprising: providing a substrate in a process chamber, the substrate having a carbon mandrel pattern and an underlying layer, the underlying layer comprising an amorphous silicon layer above a silicon nitride layer; performing a breakthrough etch process including growth of a conformal native silicon oxide layer, creating an ALD patterned structure; performing a spacer sidewall sculpting process on the ALD patterned structure; performing an amorphous silicon main etch (ME) process on the ALD patterned structure, the ME process causing a spacer oxide open and carbon mandrel removal; and performing an amorphous silicon ME over etch (OE) process on the ALD spacer oxide pattern, the ME OE process transferring the ALD spacer oxide pattern into the amorphous silicon layer, generating a first sculpted pattern comprising a first sculpted sub-structure with a trapezoidal shape.

Abstract: Provided is a method of patterning a layer on a substrate using an integration scheme, the method comprising: disposing a substrate having a structure pattern layer, a neutral layer, and an underlying layer, the structure pattern layer comprising a first material and a second material; performing a first treatment process using a first process gas mixture to form a first pattern, the first process gas comprising a mixture of CxHyFz and argon; performing a second treatment process using a second process gas mixture to form a second pattern, the second process gas comprising a mixture of low oxygen-containing gas and argon; concurrently controlling selected two or more operating variables of the integration scheme in order to achieve target integration objectives.

Abstract: Provided is a method of trimming an inorganic resist in an integration scheme, the method comprising: disposing a substrate in a process chamber, the substrate having an inorganic resist layer and an underlying layer comprising an oxide layer, a silicon nitride layer, and a base layer, the inorganic resist layer having an inorganic structure pattern; performing an inorganic resist trimming process to selectively remove a portion of the inorganic resist structure pattern on the substrate, the trimming process using a first etchant gas mixture and generating a first pattern; controlling selected two or more operating variables of the integration scheme in order to achieve target integration objectives; wherein the first etchant gas mixture comprises a fluorine-containing gas and a diluent gas; and wherein the target integration objectives include a target critical dimension (CD), a target line edge roughness (LER), a target line width roughness (LWR) and a target substrate throughput.

Abstract: Provided is a method of trimming an inorganic resist in an integration scheme, the method comprising: disposing a substrate in a process chamber, the substrate having an inorganic resist layer and an underlying layer comprising an oxide layer, a silicon nitride layer, and a base layer, the inorganic resist layer having an inorganic structure pattern; performing an inorganic resist trimming process to selectively remove a portion of the inorganic resist structure pattern on the substrate, the trimming process using a first etchant gas mixture and generating a first pattern; controlling selected two or more operating variables of the integration scheme in order to achieve target integration objectives; wherein the first etchant gas mixture comprises a fluorine-containing gas and a diluent gas; and wherein the target integration objectives include a target critical dimension (CD), a target line edge roughness (LER), a target line width roughness (LWR) and a target substrate throughput.

Abstract: Provided is a method of patterning a layer on a substrate using an integration scheme, the method comprising: disposing a substrate having a structure pattern layer, a neutral layer, and an underlying layer, the structure pattern layer comprising a first material and a second material; performing a first treatment process using a first process gas mixture to form a first pattern, the first process gas comprising a mixture of CxHyFz and argon; performing a second treatment process using a second process gas mixture to form a second pattern, the second process gas comprising a mixture of low oxygen-containing gas and argon; concurrently controlling selected two or more operating variables of the integration scheme in order to achieve target integration objectives.

Abstract: Provided is a method of forming a spacer sidewall mask, the method comprising: providing a substrate in a process chamber, the substrate having a carbon mandrel pattern and an underlying layer, the underlying layer comprising an amorphous silicon layer above a silicon nitride layer; performing a breakthrough etch process including growth of a conformal native silicon oxide layer, creating an ALD patterned structure; performing a spacer sidewall sculpting process on the ALD patterned structure; performing an amorphous silicon main etch (ME) process on the ALD patterned structure, the ME process causing a spacer oxide open and carbon mandrel removal; and performing an amorphous silicon ME over etch (OE) process on the ALD spacer oxide pattern, the ME OE process transferring the ALD spacer oxide pattern into the amorphous silicon layer, generating a first sculpted pattern comprising a first sculpted sub-structure with a trapezoidal shape.

Abstract: A search engine provider interacts with a content provider wherein the content provider provides content to the search engine provider. The content may comprise information that indicates a structure of the content provider's web pages. The search engine may use structural information to classify and extract data items from web pages, and to highlight those data items in search results with labels that identify each such data item's class.

Abstract: A liner removal process is described, wherein an excess portion of a conformal liner formed in a trench is substantially removed while reducing or minimizing damage to a bulk fill material in the trench.

Abstract: A method for performing a selective etching process is described. The method includes preparing a substrate having a silicon layer (Si) and a silicon-germanium (SiGex) layer, and selectively etching the silicon layer relative to the silicon-germanium layer using a dry plasma etching process.

Abstract: A search engine provider enters into an agreement with a content provider wherein the search engine provider agrees to provide compensation in exchange for the content provider giving content to the search engine provider. The content may comprise data that normally can't be accessed without a subscription, or any other content. The content may comprise information that indicates a structure of the content provider's web pages. The search engine may display normally inaccessible content with search results. The search engine may use structural information to classify and extract data items from web pages, and to highlight those data items in search results with labels that identify each such data item's class. A computing device determines the extent to which enhancement of the search results page using the content provider's content increased the revenue value of the page. The amount paid to the content provider may be based on this extent.

Abstract: A liner removal process is described, wherein an excess portion of a conformal liner formed in a trench is substantially removed while reducing or minimizing damage to a bulk fill material in the trench.

Abstract: This invention relates mainly to a method for constructing low cost solar electric cells and panels. The Seeback effect is used in the conversion of solar heat to electricity. Temperature differential between two sides of the solar panel is achieved with the use of thermal absorbing materials and insulating materials. Dissimilar metal wires or strips are used in series and parallel to obtain the appropriate voltage and current.