Abstract: In implementation of techniques for generating text descriptive of digital images, a computing device implements a captioning system to generate a text description of an image using a machine learning model. The captioning system identifies a negative word in the text description of the image based on a quantitative risk level for the negative word. Based on the text description of the image and the quantitative risk level, the captioning system determines an amount of suppression for use of the negative word. The captioning system then generates an updated text description of the image by applying the amount of suppression to the machine learning model to change a likelihood of using the negative word.

Abstract: Disclosed are computer-implemented methods and systems for generating text descriptive of digital images, comprising using a machine learning model to pre-process an image to generate initial text descriptive of the image; adjusting one or more inferences of the machine learning model, the inferences biasing the machine learning model away from associating negative words with the image; using the machine learning model comprising the adjusted inferences to post-process the image to generate updated text descriptive of the image; and processing the generated updated text descriptive of the image outputted by the machine learning model to fine-tune the updated text descriptive of the image.

Abstract: Disclosed are computer-implemented methods and systems for generating text descriptive of digital images, comprising using a machine learning model to pre-process an image to generate initial text descriptive of the image; adjusting one or more inferences of the machine learning model, the inferences biasing the machine learning model away from associating negative words with the image; using the machine learning model comprising the adjusted inferences to post-process the image to generate updated text descriptive of the image; and processing the generated updated text descriptive of the image outputted by the machine learning model to fine-tune the updated text descriptive of the image.

Abstract: A method for certifying a design of a liquid container onboard a vehicle for manufacture of the liquid container is provided. The method includes generating a computer geometric model of the liquid container according to the design, and executable code to reproduce dynamics and operational parameters of the vehicle, with the dynamics of the vehicle including dynamics during a vehicle maneuver that is selectable from a database of vehicle dynamics for a plurality of vehicle maneuvers. The method includes executing a simulating application to perform a simulation of liquid sloshing in the liquid container onboard the vehicle is performed subject to the dynamics and operational parameters, and iterate the simulation to refine a prediction of loads and stresses on the liquid container from the simulation produced thereby. Locations within the liquid container more vulnerable to fatigue-risk are identified based on the prediction, and output for certification of the design.

Abstract: Disclosed are computer-implemented methods and systems for generating text descriptive of digital images, comprising using a machine learning model to pre-process an image to generate initial text descriptive of the image; adjusting one or more inferences of the machine learning model, the inferences biasing the machine learning model away from associating negative words with the image; using the machine learning model comprising the adjusted inferences to post-process the image to generate updated text descriptive of the image; and processing the generated updated text descriptive of the image outputted by the machine learning model to fine-tune the updated text descriptive of the image.

Abstract: An apparatus for building an artificial-intelligence system is provided. The apparatus accesses images of a real-world scene and generates an image of a simulated object corresponding to a real-world object using a first generative adversarial network (GAN). The apparatus inserts the image of the simulated object into the images of the real-world scene to produce images of the real-world scene including the simulated object. The apparatus applies the images of the real-world scene including the simulated object to a second GAN to remove visual artifacts thereby producing a training set of images of the real-world scene including the simulated object. The apparatus trains an artificial-intelligence algorithm using the training set of images to build the artificial-intelligence system to detect the real-world object in further images of the real-world scene and outputs the artificial-intelligence system for deployment on an autonomous vehicle.

Abstract: An apparatus for building an artificial-intelligence system is provided. The apparatus accesses images of a real-world scene and generates an image of a simulated object corresponding to a real-world object using a first generative adversarial network (GAN). The apparatus inserts the image of the simulated object into the images of the real-world scene to produce images of the real-world scene including the simulated object. The apparatus applies the images of the real-world scene including the simulated object to a second GAN to remove visual artifacts thereby producing a training set of images of the real-world scene including the simulated object. The apparatus trains an artificial-intelligence algorithm using the training set of images to build the artificial-intelligence system to detect the real-world object in further images of the real-world scene and outputs the artificial-intelligence system for deployment on an autonomous vehicle.

Abstract: A method includes executing a simulating application to perform a first simulation of liquid sloshing in a hull onboard a vehicle subject to dynamics and operational parameters to produce a first prediction of loads and stresses on a portion of the hull that in a design of the liquid container, but not in a first computer geometric model of the hull, has a component of the components integrated or assembled thereto. A second computer geometric model of the portion of the hull with the component is generated and the first prediction of loads and stresses are applied thereto. The method includes executing the simulating application to perform a second simulation subject to the dynamics and operational parameters to produce a second prediction of loads and stresses on the component. The second prediction of loads and stresses on the component are output for certification of the design.

Abstract: A method for certifying a design of a liquid container onboard a vehicle for manufacture of the liquid container is provided. The method includes generating a computer geometric model of the liquid container according to the design, and executable code to reproduce dynamics and operational parameters of the vehicle, with the dynamics of the vehicle including dynamics during a vehicle maneuver that is selectable from a database of vehicle dynamics for a plurality of vehicle maneuvers. The method includes executing a simulating application to perform a simulation of liquid sloshing in the liquid container onboard the vehicle is performed subject to the dynamics and operational parameters, and iterate the simulation to refine a prediction of loads and stresses on the liquid container from the simulation produced thereby. Locations within the liquid container more vulnerable to fatigue-risk are identified based on the prediction, and output for certification of the design.