Abstract: Systems, computer-implemented methods, and instructions encoded in machine-accessible storage media are provided for determining manufacturability of an integrated circuit layout. A computer-implemented method includes receiving a layout describing the integrated circuit to be manufactured by a semiconductor manufacturing process. The method also includes generating a differentiable manufacturability parameter as an output of a machine learning model using the layout, the machine learning model being trained to generate the differentiable manufacturability parameter. The differentiable manufacturability parameter describes the manufacturability of the integrated circuit by the semiconductor manufacturing process.

Abstract: Systems, computer-implemented methods, and instructions encoded in machine-accessible storage media are provided for determining manufacturability of an integrated circuit layout. A computer-implemented method includes receiving a layout describing the integrated circuit to be manufactured by a semiconductor manufacturing process. The method also includes generating a differentiable manufacturability parameter as an output of a machine learning model using the layout, the machine learning model being trained to generate the differentiable manufacturability parameter. The differentiable manufacturability parameter describes the manufacturability of the integrated circuit by the semiconductor manufacturing process.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for improved image segmentation using hyperspectral imaging. In some implementations, a system obtains image data of a hyperspectral image, the image data comprising image data for each of multiple wavelength bands. The system accesses stored segmentation profile data for a particular object type that indicates a predetermined subset of the wavelength bands designated for segmenting different region types for images of an object of the particular object type. The system segments the image data into multiple regions using the predetermined subset of the wavelength bands specified in the stored segmentation profile data to segment the different region types. The system provides output data indicating the multiple regions and the respective region types of the multiple regions.

Abstract: A computer-implemented method for integrated circuit routing is described. The computer-implemented method comprising receiving a description of interconnected terminals of an integrated circuit with a wiring route electrically coupling the interconnected terminals and configuring a simulated environment defined via a plurality of voxels based on the description. The individual voxels included in the plurality of voxels each correspond to a spatial representation for a corresponding region of a layout associated with the integrated circuit. The computer-implemented method further includes determining local contributions of the individual voxels to a characteristic metric of the integrated circuit based on an electromagnetic simulation of the integrated circuit and revising the wiring route based on the local contributions of the individual voxels.

Abstract: A computer-implemented method for integrated circuit routing is described. The computer-implemented method comprising receiving a description of interconnected terminals of an integrated circuit with a wiring route electrically coupling the interconnected terminals and configuring a simulated environment defined via a plurality of voxels based on the description. The individual voxels included in the plurality of voxels each correspond to a spatial representation for a corresponding region of a layout associated with the integrated circuit. The computer-implemented method further includes determining local contributions of the individual voxels to a characteristic metric of the integrated circuit based on an electromagnetic simulation of the integrated circuit and revising the wiring route based on the local contributions of the individual voxels.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for improved image segmentation using hyperspectral imaging. In some implementations, a system obtains image data of a hyperspectral image, the image data comprising image data for each of multiple wavelength bands. The system accesses stored segmentation profile data for a particular object type that indicates a predetermined subset of the wavelength bands designated for segmenting different region types for images of an object of the particular object type. The system segments the image data into multiple regions using the predetermined subset of the wavelength bands specified in the stored segmentation profile data to segment the different region types. The system provides output data indicating the multiple regions and the respective region types of the multiple regions.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for image segmentation and chemical analysis using machine learning. In some implementations, a system obtains a hyperspectral image that includes a representation of an object. The system segments the hyperspectral image to identify regions of a particular type on the object. The system generates a set of feature values derived from image data for different wavelength bands that is located in the hyperspectral image in the identified regions of the particular type. The system generates a prediction of a level of one or more chemicals in the object based on an output produced by a machine learning model in response to the set of feature values being provided as input to the machine learning model. The system provides data indicating the prediction of the level of the one or more chemicals in the object.

Abstract: Systems, computer-implemented methods, and instructions encoded in machine-accessible storage media are provided for determining manufacturability of an integrated circuit layout. A computer-implemented method includes receiving a layout describing the integrated circuit to be manufactured by a semiconductor manufacturing process. The method also includes generating a differentiable manufacturability parameter as an output of a machine learning model using the layout, the machine learning model being trained to generate the differentiable manufacturability parameter. The differentiable manufacturability parameter describes the manufacturability of the integrated circuit by the semiconductor manufacturing process.

Abstract: A computer-implemented method for integrated circuit routing is described. The computer-implemented method comprising receiving a description of interconnected terminals of an integrated circuit with a wiring route electrically coupling the interconnected terminals and configuring a simulated environment defined via a plurality of voxels based on the description. The individual voxels included in the plurality of voxels each correspond to a spatial representation for a corresponding region of a layout associated with the integrated circuit. The computer-implemented method further includes determining local contributions of the individual voxels to a characteristic metric of the integrated circuit based on an electromagnetic simulation of the integrated circuit and revising the wiring route based on the local contributions of the individual voxels.

Abstract: Embodiments of a system and method for generating integrated circuit layouts are described herein. A computer implemented method for generating integrated circuit layouts includes receiving a first layout for an integrated circuit, segmenting the first layout into a plurality of different patches, each patch of the plurality of patches describing a discrete portion of the first layout, identifying a non-compliant patch of the plurality of patches, the non-compliant patch violating a design rule governing the manufacture of the integrated circuit, generating a transformation of the non-compliant patch using a machine learning model, and generating a second layout using the transformation and the first layout, where the second layout is compliant with the design rule.

Abstract: Embodiments of a system and method for generating integrated circuit layouts are described herein. A computer implemented method for generating integrated circuit layouts includes receiving a first layout for an integrated circuit, segmenting the first layout into a plurality of different patches, each patch of the plurality of patches describing a discrete portion of the first layout, identifying a non-compliant patch of the plurality of patches, the non-compliant patch violating a design rule governing the manufacture of the integrated circuit, generating a transformation of the non-compliant patch using a machine learning model, and generating a second layout using the transformation and the first layout, where the second layout is compliant with the design rule.

Abstract: Aspects of the technology include establishing a primary communication link between a communication system of a first balloon and a communication system of a second balloon, detecting a movement of the second balloon relative to the first balloon that is expected to cause the primary communication link to become unavailable at a given time during the movement, establishing an RF communication link between an RF communication system of the first balloon and an RF communication system of the second balloon, detecting that the movement of the second balloon relative to the first balloon is such that the primary communication link between the communication system of the first balloon and the optical communication system of the second balloon can be re-established, and re-establishing the primary communication link between the communication system of the first balloon and the communication system of the second balloon.

Abstract: A method of establishing one or more links for an integrated access and backhaul for a network, where the network includes a non-terrestrial node and a terrestrial node, includes determining a plurality of links to form between a non-terrestrial node and a number of nodes in the network and causing the plurality of links to be formed. The method also includes determining a plurality of routing paths for backhaul between the non-terrestrial node to a central server, providing instructions for backhaul between the non-terrestrial node and the central server using the plurality of routing paths, and transmitting a first set of data to backhaul via a first routing path of the plurality of routing paths and a second set of data to backhaul via a second routing path of the plurality of routing paths.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for image segmentation and chemical analysis using machine learning. In some implementations, a system obtains a hyperspectral image that includes a representation of an object. The system segments the hyperspectral image to identify regions of a particular type on the object. The system generates a set of feature values derived from image data for different wavelength bands that is located in the hyperspectral image in the identified regions of the particular type. The system generates a prediction of a level of one or more chemicals in the object based on an output produced by a machine learning model in response to the set of feature values being provided as input to the machine learning model. The system provides data indicating the prediction of the level of the one or more chemicals in the object.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for improved image segmentation using hyperspectral imaging. In some implementations, a system obtains image data of a hyperspectral image, the image data comprising image data for each of multiple wavelength bands. The system accesses stored segmentation profile data for a particular object type that indicates a predetermined subset of the wavelength bands designated for segmenting different region types for images of an object of the particular object type. The system segments the image data into multiple regions using the predetermined subset of the wavelength bands specified in the stored segmentation profile data to segment the different region types. The system provides output data indicating the multiple regions and the respective region types of the multiple regions.

Abstract: Image data is obtained that indicates an extent to which one or more objects reflect, scatter, or absorb light at each of multiple wavelength bands, where the image data was collected while a conveyor belt was moving the object(s). The image data is preprocessed by performing an analysis across frequencies and/or performing an analysis across a representation of a spatial dimension. A set of feature values is generated using the image preprocessed image data. A machine-learning model generates an output using to the feature values. A prediction of an identity of a chemical in the one or more objects or a level of one or more chemicals in the object(s) is generated using the output. Data is output indicating the prediction of the identity of the chemical in the object(s) or the level of the one or more chemicals in at least one of the one or more objects.

Abstract: A method and apparatus are provided for nulling a radio frequency (RF) beam for a high-altitude platform (HAP). A transmitter generates an RF signal. A primary antenna system generates an RF beam based on the RF signal. One or more processors determine a result indicating whether to modify the RF beam. When the result indicates to modify the RF beam, a detachable nulling subassembly generates nulling signals based on the RF signal to modify the RF beam generated by the primary antenna system.

Abstract: According to a first aspect, there is provided an adaptive cooking device that includes: a cooking chamber configured to receive a food product, an antenna assembly, an RF power source, a sensor assembly coupled to the cooking chamber and comprising a plurality of sensors, each sensor configured to obtain a measurement characterizing a cooking process in real-time, and one or more sensors of the plurality of sensors configured to obtain a different type of the measurement, and a controller coupled to the antenna assembly, the sensor assembly, and the RF power source, wherein the controller is configured to: receive the measurement characterizing the cooking process from the sensor assembly, process the measurement to determine a modified cooking process, and operate the antenna assembly and the RF power source in accordance with the modified cooking process in real-time.

Abstract: Aspects of the disclosure provide an antenna system for a high-altitude platform (HAP). The antenna system may include a central panel including a first set of antenna elements. The antenna system may also include a plurality of auxiliary panels arranged around the central panel and at an angular offset from the central panel. Each auxiliary panel of the set of auxiliary panels may include a second plurality of antenna elements. The first plurality of antenna elements may be configured to provide network coverage within a first area having a first radius and each of the second sets of antenna elements are configured to provide network coverage within a second area beyond the first radius.

Abstract: An in-ear device includes a tympanic membrane measurement unit (TMMU) and an audio package configured to emit sound. The device is configured to measure a movement of a tympanic membrane in an ear using the TMMU caused by external sound received by the tympanic membrane, analyze at least the movement of the tympanic membrane measured by the TMMU using a predictive model trained by a machine learning technique to generate a waveform of cancellation sound that will destructively interfere with the external sound when received by the tympanic membrane, and output the cancellation sound from the audio package to destructively interfere with external sound received by the tympanic membrane.