Abstract: The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment.

Abstract: An illustrative embodiment of a computer-implemented process for non-leading computer aided detection of features of interest in a dataset, designates a particular formation using a computer recognizable gesture to identify a gestured location in an analyzed view of the dataset in response to a user identifying the particular formation in the analyzed view. The dataset is generated by a computer and representative of a portion of an object characterized by the dataset. Responsive to identifying the gestured location, the particular formation is displayed to the user, and a composition is revealed including additional structural imagery, functional imagery and findings resulting from machine learning and analysis. Responsive to revealing the composition to the user, the user is prompted to select performance of accept selection, reject selection or modify selection with regard to the particular formation displayed.

Abstract: Mechanisms are provided to implement a medical condition base cartridge generator. The mechanisms ingest an electronic corpus of medical content and generate a medical condition base cartridge for a medical condition. The medical condition base cartridge is a pluggable cartridge comprising insight data structures that specify an association of clinical attributes of patients with the medical condition and a treatment for the medical condition. The mechanisms install the medical condition base cartridge as a resource for performing a cognitive operation.

Abstract: Network flow classification can include clustering a network flow database into a number of at least one of applications and network flows. Network flow classification can include classifying the number of the at least one of applications and network flows.

Abstract: Methods, systems, and computer program products for expressive temporal predictions over semantically-driven time windows are provided herein. A computer-implemented method includes identifying, within a knowledge graph pertaining to a given prediction, a subset of the knowledge graph related to one or more predicted training examples, wherein the subset comprises (i) a set of nodes and (ii) one or more relationships among the set of nodes; determining, for the identified subset, one or more snapshots of the knowledge graph relevant to the given prediction; quantifying a validity window for the one or more predicted training examples, wherein the validity window comprises a temporal bound for prediction validity; and computing a validity window for the given prediction based on the quantified validity window for the one or more predicted training examples.

Abstract: Methods, computer program products, and systems are presented. The methods computer program products, and systems can include, for instance: determining an insertion interval of a row for insertion into a decision table; and guiding insertion of the row for insertion into the decision table based on a result of the determining.

Abstract: Systems and methods are provided for accurately setting notification priority levels for applications on a user device. An example system includes a user device and a management server. When an application generates a notification, it provides a priority level for the notification. A management agent executing on the user device can detect the notification and its assigned priority level, determine a predicted priority level using a prediction engine or prediction server, and cause the application the replace or update the assigned priority level based on the predicted priority level. The management agent can then receive user actions related to that notification from the application, and use that information to determine an observed priority level. The prediction engine or prediction server can be updated based on the observed priority level, thereby dynamically increasing the accuracy of predictions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

Abstract: A lithography apparatus includes a detector that detects an original-side mark image and a substrate-side mark image via a projection optical system, and a controller. The detector generates refocusable light field image data that includes the original-side mark image and the substrate-side mark image. The controller performs, based on the light field image data obtained from the detector, a refocus operation of reconstructing a plurality of images different in position in a focus direction and adjusts a position of at least one of the original holder and the substrate holder based on the plurality of images reconstructed by the refocus operation.

Abstract: A movable body apparatus includes a base member, a movable body that is movable at least two-dimensionally, parallel to a predetermined plane, on the base member, a planar motor of a magnetic levitation method having a stator provided at the base member and a mover provided at the movable body, a measurement system that measures a position of the movable body in a direction parallel to the predetermined plane, and a controller. The controller limits movement of the movable body in the direction parallel to the predetermined plane by applying, to the movable body, a driving force generated by the planar motor, directed from the movable body to the base member in a direction intersecting the predetermined plane.

Abstract: A lithographic projection apparatus is disclosed in which a space between the projection system and a sensor is filled with a liquid.

Abstract: A substrate processing apparatus includes: a rotary cylindrical member (DR) that includes a cylindrical supporting surface curved with a constant radius from a predetermined center line (AX2) and that feeds a substrate (P) in a length direction of the substrate; a processing mechanism that performs a predetermined process on the substrate at a specific position (PA, EL2) of a part of the substrate; a scale member (SD) that rotates about the center line along with the rotary cylindrical member so as to measure a displacement in a circumferential direction of the supporting surface of the rotary cylindrical member or a displacement in a direction of the center line of the rotary cylindrical member and that includes a scale portion (GP) carved in a ring shape; and a reading mechanism (EN1, EN2) that faces the scale portion, that is disposed in substantially a same direction as the specific position when viewed from the center line, and that reads the scale portion.

Abstract: An immersion lithography apparatus comprises a temperature controller configured to adjust a temperature of a projection system, a substrate and a liquid towards a common target temperature. Controlling the temperature of these elements and reducing temperature gradients may improve imaging consistency and general lithographic performance. Measures to control the temperature may include controlling the immersion liquid flow rate and liquid temperature, for example, via a feedback circuit.

Abstract: A lithographic projection apparatus is disclosed for use with an immersion liquid positioned between the projection system and a substrate. Several methods and mechanism are disclosed to protect components of the projection system, substrate table and a liquid confinement system. These include providing a protective coating on a final element of the projection system as well as providing one or more sacrificial bodies upstream of the components. A two component final optical element of CaF2 is also disclosed.

Abstract: A target image-capture device may be configured to capture an image of a target that is made into plasma when irradiated with laser light and generates extreme-ultraviolet-light. The target image-capture device may include a droplet detector configured to detect passage of a droplet output as the target, and output a detection signal, an illumination light source, an image capturing element, a shutter device, and a controller configured to output, to the image capturing element, an exposure signal allowing the image capturing element to perform image capturing, and output, to the shutter device, a shutter open/close signal allowing a shutter to perform an open and close operation upon input of the detection signal. The controller may output the shutter open/close signal to the shutter device to make the shutter closed during when the droplet is irradiated with the laser light so that the plasma is generated.

Abstract: An inspection method determines values of profile parameters of substrate patterns. A baseline substrate with a baseline pattern target (BP) is produced that has a profile described by profile parameters, for example CD (median critical dimension), SWA (side wall angle) and RH (resist height). Scatterometry is used to obtain first and second signals from first and second targets. Values of differential pattern profile parameters are calculated using a Bayesian differential cost function based on a difference between the baseline pupil and the perturbed pupil and dependence of the pupil on pattern profile parameters. For example, the difference is measured between a baseline process and a perturbed process for stability control of a lithographic process. Fed-forward differential stack parameters are also calculated from observations of stack targets on the same substrates as the pattern targets.

Abstract: An alignment apparatus for aligning a substrate, and a substrate processing system including such alignment apparatus. The alignment apparatus includes an alignment base for supporting the substrate and/or a substrate support member. A force generating device applies a contact force on the substrate. The force generating device includes an arm including a rigid proximal end and a rigid distal end. The distal end is provided with a contact section for contacting an edge of the substrate and an elastically deformable arm section extending between the proximal and distal ends. The connection part connects the proximal end to the alignment base. The arm is movable with respect to the alignment base via the connection part. The alignment apparatus also includes an actuator for causing a displacement of the proximal end, whereby the contact force, defined by the elastically deformable arm section, is applied to the substrate by the contact section.

Abstract: An exposure apparatus exposes a substrate with illumination light via a projection optical system, and includes a frame member, a mark detection system that detects a mark of the substrate, a mask stage system having a first movable body to hold a mask, a first encoder system having first heads that each irradiate a first measurement beam to a first grating section, a substrate stage system having a second movable body to hold the substrate, a second encoder system having second heads that each irradiate a second measurement beam to a second grating section, and a controller that controls driving of the first movable body and of the second movable body, based on measurement information of the first and second encoder systems. In each of an exposure operation and a detection operation, the positional information of the second movable body is measured by the second encoder system.

Abstract: A method for manufacturing an integrated circuit includes scanning a wafer with respect to a catadioptric projection objective and imaging a pattern on a mask onto a wafer while scanning the wafer. The imaging includes illuminating the mask with radiation; imaging, using the radiation, the pattern into a first intermediate image, the first intermediate image to a second intermediate image, and the second intermediate image into an image field arranged in an image surface where the wafer is arranged; and, manipulating one or more of optical elements while scanning the wafer to reduce errors in the image at the image field. A concave mirror arranged in a region of a pupil surface reflects the radiation. The projection objective also includes mirrors to deflect the radiation from the object field towards the concave mirror and to deflect the radiation from the concave mirror towards the image field.

Abstract: A support apparatus for a lithographic apparatus has an object holder and an extraction body radially outward of the object holder. The object holder is configured to support an object. The extraction body includes an extraction opening configured to extract fluid from a top surface of the support apparatus. The extraction body is spaced from the object holder such that the extraction body is substantially decoupled from the object holder. The extraction body comprises a projection configured such that it surrounds the object holder and such that, in use, a layer of liquid is retained on the projection and in contact with an object supported on the object holder.