Abstract: A medical scope device such as an endoscope is produced using a cast aluminum process including a molten casting aluminum alloy including a maximum of 0.2-0.3% Si and at least 5% Zn. The process includes providing an investment casting mold, casting the aluminum alloy in the mold to create a component and removing the mold from the component, post-machining the component to meet a desired specification, and after post-machining the component, performing surface finishing, such as centrifugal barrel finishing (CBF) sufficient to remove impurities on casting surfaces by 2-3 mils, then coating the component with a micro-crystalline aluminum anodic coating of at least 0.5 mil thickness. A medical scope and product-by-process is also provided employing such techniques.

Abstract: A medical scope device such as an endoscope is produced using a cast aluminum process including a molten casting aluminum alloy including a maximum of 0.2-0.3% Si and at least 5% Zn. The process includes providing an investment casting mold, casting the aluminum alloy in the mold to create a component and removing the mold from the component, post-machining the component to meet a desired specification, and after post-machining the component, performing surface finishing, such as centrifugal barrel finishing (CBF) sufficient to remove impurities on casting surfaces by 2-3 mils, then coating the component with a micro-crystalline aluminum anodic coating of at least 0.5 mil thickness. A medical scope and product-by-process is also provided employing such techniques.

Abstract: A model evaluation system evaluates the effect of a feature value at a particular time in a time-series data record on predictions made by a time-series model. The time-series model may make predictions with black-box parameters that can impede explainability of the relationship between predictions for a data record and the values of the data record. To determine the relative importance of a feature occurring at a time and evaluated at an evaluation time, the model predictions are determined on the unmasked data record at the evaluation time and on the data record with feature values masked within a window between the time and the evaluation time, permitting comparison of the evaluation with the features and without the features. In addition, the contribution at the initial time in the window may be determined by comparing the score with another score determined by masking the values except for the initial time.

Abstract: The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.

Abstract: A medical scope device such as an endoscope is produced using a cast aluminum process including a molten casting aluminum alloy including a maximum of 0.2 - 0.3% Si and at least 5% Zn. The process includes providing an investment casting mold, casting the aluminum alloy in the mold to create a component and removing the mold from the component, post-machining the component to meet a desired specification, and after post-machining the component, performing surface finishing, such as centrifugal barrel finishing (CBF) sufficient to remove impurities on casting surfaces by 2 - 3 mils, then coating the component with a micro-crystalline aluminum anodic coating of at least 0.5 mil thickness. A medical scope and product-by-process is also provided employing such techniques.

Abstract: A model visualization system analyzes model behavior to identify clusters of data instances with similar behavior. For a selected feature, data instances are modified to set the selected feature to different values evaluated by a model to determine corresponding model outputs. The feature values and outputs may be visualized in an instance-feature variation plot. The instance-feature variation plots for the different data instances may be clustered to identify latent differences in behavior of the model with respect to different data instances when varying the selected feature. The number of clusters for the clustering may be automatically determined, and the clusters may be further explored by identifying another feature which may explain the different behavior of the model for the clusters, or by identifying outlier data instances in the clusters.

Abstract: The disclosed embodiments include computer-implemented systems and processes that predict occurrences of targeted attrition events using trained artificial-intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a targeted participant during a first temporal interval. Based on an application of a trained artificial-intelligence process to the input dataset, the apparatus may generate output data representative of a predicted likelihood of an occurrence of an attrition event involving the targeted participant during a second temporal interval that is disposed subsequent to the first temporal interval, and that is separated from the first temporal interval by a buffer interval.

Abstract: The disclosed embodiments include computer-implemented processes that flexibly and dynamically analyze a machine learning process, and that generate analytical output characterizing an operation of the machine learning process across multiple analytical periods. For example, an apparatus may receive an identifier of a dataset associated with the machine learning process and feature data that specifies an input feature of the machine learning process. The apparatus may access at least a portion of the dataset based on the received identifier, and obtain, from the accessed portion of the dataset, a feature vector associated with the machine learning process.

Abstract: A modeling system trains a recurrent machine-learned model by determining a latent distribution and a prior distribution for a latent state. The parameters of the model are trained based on a divergence loss that penalizes significant deviations between the latent distribution the prior distribution. The latent distribution for a current observation is a distribution for the latent state given a value of the current observation and the latent state for the previous observation. The prior distribution for a current observation is a distribution for the latent state given the latent state for the previous observation independent of the value of the current observation, and represents a belief about the latent state before input evidence is taken into account.

Abstract: A method of packaging an ink tank for shipment, the method comprising: (a) sealing a first substratum to an ink tank to inhibit fluid communication between an interior of the ink tank and an external environment by way of an ink outlet port of the ink tank, the resultant seal between the first substratum and the ink tank includes at least one of an apex at least partially defined by two substantially linear segments being angled from one another between about 20 degrees to about 160 degrees and fractions separating portions of the substrate from one another; and (b) sealing a second substratum to the ink tank to inhibit fluid communication between the interior of the ink tank and the external environment by way of an ink vent of the ink tank, where the first substratum and the second substratum are removable from the ink tank.

Abstract: Printing systems such as those comprising a printing device operable for depositing one or more inks upon a substrate and a drying device, such as one operable for emitting radiation having a pre-selected electromagnetic wavelength, for the purpose of drying the one or more inks in a predetermined time period subsequent to the deposition of the one or more inks upon the substrate, wherein the printing device and the drying device are operated at about the same moving speed. Methods of printing, such as those comprising depositing one or more inks onto a substrate using a printing device and drying the one or more deposited inks using a drying device, such as one operable for emitting pre-selected wavelengths of energy that are focused onto the one or more deposited inks in a predetermined time period subsequent to ink deposition, wherein the depositing and the drying are synchronized.

Abstract: Ink delivery systems achieve balanced ink flow by positioning two or more ink chambers around ink ejection mechanisms in a printhead. A plurality of pie-shaped ink chambers may be arranged in a circle above an ink ejection mechanism, which provides short ink paths from each ink chamber, and ink paths having approximately the same length. This fosters even ink flow rates and equal pressure drop/loss of ink supplies, thereby improving ink feeds to a printhead and providing improved jetting efficiency and printhead performance.

Abstract: A process for fabricating an integrated circuit package. Metal is plated up on a substrate to provide a plurality of contacts pads and a plurality of fiducial markings on a periphery of the contacts. A transparent mask is selectively deposited on the substrate, over the fiducial markings. A semiconductor die is mounted on the substrate such that the contact pads circumscribe the semiconductor die and the semiconductor die is wire bonded to ones of the contact pads. The wire bonds are encapsulated and the semiconductor die and contact pads are covered in a molding material. The substrate is selectively etched to thereby etch away the substrate underneath the contact pads and the semiconductor die. The integrated circuit package is singulated from other integrated circuit packages by sawing using the fiducial markings.

Abstract: A micro-fluid ejection device structure, a multi-fluid cartridge containing the ejection device structure, and methods for making the ejection device structure and cartridge. The micro-fluid ejection device structure includes a fluid supply body containing at least three fluid supply slots therein. An ejection head substrate having fluid feed slots therein is attached to the fluid supply body. Each of the fluid supply slots in the body is in flow communication with at least one of the fluid feed slots in the substrate. A plurality of adhesive bond lines adhesively attach the ejection head substrate and the fluid supply body to one another. Each of the adhesive bond lines have a width of less than about 600 microns and are located between adjacent ones of the fluid supply slots in the body.

Abstract: A method of assembling a print head that includes the steps of: (a) providing a print head base including a nozzle and at least one ink channel; (b) mounting in fluid communication with the at least one ink channel of the print head base an ink regulator that includes: (i) a pressurized chamber including an ink inlet in fluid communication with an ink source, an ink outlet in fluid communication with the at least one ink channel of the print head base, and an exterior flexible wall having an inner surface facing an interior of the pressurized chamber, (ii) a valve biased to restrict fluid communication between the ink source and the pressurized chamber, where the exterior flexible wall actuates the valve to overcome the bias in response to a predetermined pressure differential across the exterior flexible wall to provide fluid communication between the ink source and the pressurized chamber, where the fluid communication between the pressurized chamber and the ink source decreases the pressure differential ac

Abstract: A multi-fluid body and an ejection head substrate connected in fluid flow communication with the multi-fluid body for ejecting multiple fluids therefrom. The multi-fluid body includes at least two segregated fluid chambers. Independent fluid supply paths lead from each of the fluid chambers providing fluid to multiple fluid flow paths in the ejection head substrate. The ejection head substrate is attached adjacent an ejection head area of the body. The fluid flow paths in the ejection head substrate have a flow path density of greater than about one flow paths per millimeter.

Abstract: A method for manufacturing an inkjet print cartridge and an inkjet cartridge produced thereby are disclosed. An inkjet print cartridge in accordance with one aspect includes a component of the inkjet print cartridge and an applied adhesive on at least a portion of the component, wherein the applied adhesive is formed from an adhesive having a rheology viscosity ratio ?i/?min of from 1.0 to less than 2.1. The method in accordance with one aspect includes applying an adhesive onto at least a portion of a component of an inkjet print cartridge at an application temperature, T?, and heating the adhesive from an initial temperature, Ti, to a cure temperature for the adhesive, Tc. The adhesive has a rheology cure profile characterized by at least one of the following parameters: a) a rheology viscosity ratio ?i/?min of from 1.0 to less than 2.

Abstract: A printing cartridge including a body, the body having a base and a tower defining a passageway. The tower is made from a first polymer material, and has a proximal end and a distal end. The proximal end is attached to the base. The distal end includes a surface. A frame, made of a second polymer material different from the first polymer material, is attached to the surface of the tower. A filter is attached to the frame and positioned to extend over the passageway.

Abstract: An apparatus for a laser transmission welding process for attaching a synthetic filter material to a filter tower frame in an ink jet printer cartridge. The apparatus includes a laser beam source and a filter clamping fixture containing a base, slide rods attached on first ends thereof to the base, an optics support plate attached to second ends of the slide rods, a movable platform for holding an ink cartridge slidably disposed on the slide rods between the base and the optics support plate, a platform moving device for translating the platform to and from a laser welding position, a laser beam transparent plate suspended by support legs from the optics support plate to a position between the movable platform and the optics support plate. The apparatus greatly improves synthetic filter attachment to a filter tower frame in an ink cartridge.