Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. In one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural networks for performing the machine learning task, wherein each candidate neural network comprises a plurality of instances of a layer block composed of a plurality of layers, for each candidate neural network, selecting a respective type for each of the plurality of layers from a set of layer types that comprises, training the candidate neural network and evaluating performance scores for the trained candidate neural networks as applied to the machine learning task, and determining a final neural network for performing the machine learning task based at least on the performance scores for the candidate neural networks.

Abstract: Disclosed is a method for automatically generating interactive test cases. The method comprises: after a UI of an application program is displayed, traversing all views in a view tree corresponding to the UI of the application program, and recording a path, in the view tree, of each view therein that can be clicked on, so as to obtain a set of path information, in the view tree, of all the views that can be clicked on in the UI; and respectively generating a corresponding test case for each piece of path information in the set: in the test case, according to path information, in the view tree, of a view under test, finding the view in the UI interface of the application program, and triggering a click event therefore, that is, completing a click interaction test on the view. In the present invention, there is no strict requirements for the type and the running environment of an application program.

Abstract: The present application discloses a traffic light control method for an urban road network based on expected return estimation, which uses C-V2X wireless communication technology to obtain real-time information of all vehicles and traffic state in the road network from vehicle-mounted terminals, and adaptively and dynamically controls the phase transformation of the traffic light. According to the present application, the expected returns of keeping the current phase and executing phase switch are calculated by estimating the timely driving distance and the future driving distance of the passable vehicles in the next green light duration in combination with the proposed road priority traffic index. By comparing the expected returns of keeping the current phase or switching to other phases, the best phase is selected, so as to make as many passable vehicles travel farther as possible in the next green light duration. Therefore, the efficiency of traffic will be improved.

Abstract: The present application discloses a method and a device for estimating the position of a networked vehicle based on independent non-uniform increment sampling. By mapping a laser radar point cloud to a spatiotemporal aligned image, independent non-uniform increment sampling is carried out on the mapping points falling in an advanced semantic constraint region of the image according to a point density of the depth interval where the mapping points are located, and the virtual mapping points generated by sampling are reversely mapped to the original point cloud space and merged with the original point cloud, and the combined point cloud is used to estimate the position of the networked vehicle based on a deep learning method, so as to solve the inaccurate position estimation problem of sheltered or remote networked vehicles due to the sparseness or missing of its own point cloud clusters.

Abstract: A sintered neodymium iron boron magnet as shown in the formula RxT100-x-y1-y2-zMy1Ay2Bz is provided according to the present application, which specifically includes three different technical solutions.

Abstract: Global and local alignment energies are used in an image contrast metric. The image contrast metric can be used to find optical targets. Some pixels from a gradient magnitude image and a context range image from an optical image can be used to determine the image contrast metric. A heatmap from the image contrast metrics across part of a wafer can then be used to make a list of targets. Upper and lower confidence values can be applied to rank the available targets.

Abstract: The present disclosure provides methods for shunting clustered gateways, which relate to the field of computer technologies, and in particular, relate to the technical field of data transmission. A specific implementation solution is: in response to receiving a first packet sent by a target internal network machine, a first hash value is acquired, wherein the first hash value is generated by a shunt of a public network gateway cluster, and the shunt is configured to perform a hash calculation on the first packet based on a pre-configured port dictionary; a target gateway machine is selected from the public network gateway cluster according to the first hash value; and the first packet is sent to the target gateway machine.

Abstract: The present invention provides substantia nigra organoids on silica iSECnMs and method of producing the same. The present invention also provides method of cell therapy including the substantia nigra organoids on silica iSECnMs. It also provides a method of promoting differentiation of neural stem cells to neurons includes culturing the neural stem cells on a nanostructure having a plurality of nanozigzags or nanohelices fabricated from SiO2 or TiOx.

Abstract: Biocompatible silica inorganic sculptured extracellular nanomatrices (iSECnMs) of silica nanozigzags are deposited by glancing angle deposition (GLAD), to achieve induction of specific differentiation without growth factors. The nanostructure includes a plurality of nanozigzags. The nanozigzags include SiO2 and the nanozigzags having a pitch of 80 nm to 250 nm, and a contact depth of 90 nm to 260 nm. A method of cell therapy including substantia nigra organoids formed on silica iSECnMs is also provided.

Abstract: A battery, including a laminated cell, a first housing configured to accommodate the laminated cell, and a second housing mounted to the first housing, where the laminated cell includes an electrode assembly and a first tab. The electrode assembly includes a first side face, where the first tab is connected to the first side face, and the first housing, the first tab, and the first side face together define an injection space. The second housing is provided with an injection opening, where a projection of the injection space onto the second housing covers at least part of the injection opening. This application further provides an electric apparatus with the foregoing battery. This application can improve injection efficiency.

Abstract: Global and local alignment energies are used in an image contrast metric. The image contrast metric can be used to find optical targets. Some pixels from a gradient magnitude image and a context range image from an optical image can be used to determine the image contrast metric. A heatmap from the image contrast metrics across part of a wafer can then be used to make a list of targets. Upper and lower confidence values can be applied to rank the available targets.

Abstract: Metal-free compositions for solar-reflective infrared-emissive coatings and methods of producing the same. The paints are suitable for reducing the temperatures of objects below ambient temperatures between sunset and sunrise (nighttime) and part or full daytime (between sunrise and sunset) when such objects are subjected to direct sunlight. Such a solar-reflective infrared-emissive paint may include a particle-polymer composite containing particles in a polymeric matrix, wherein the particles are nanoparticles or microparticles, the paint does not contain a metallic component, and the paint exhibits high reflectance for the solar spectrum wavelengths of 0.3 to 3 micrometers and high emissivity for wavelengths of 8 to 13 micrometers.

Abstract: X-ray microscopy tomography scanning systems are not constrained by continuous scanning trajectories like in medical scanners. In fact, the source and detector can be held stationary during subsequent image capture producing a discrete sampling pattern. For such systems, a method of producing an optimized, even illumination of the object by choosing source/detector locations on a surface of an imaginary cylinder surrounding the object is disclosed. The locations, in one example, form a regular lattice with even coverage on the surface of that cylinder, rather than at locations along a continuous curve such as a helix. Using this method, the effective pitch may be increased beyond the theoretical limit imposed by helical scanning, allowing a greater range of y-axis coverage for the same number of projection angles, corresponding to an increase in throughput.

Abstract: A spectrum measurement and estimation method for tomographic reconstruction, beam hardening correction, dual-energy CT and system diagnosis, etc., comprises determining the spectra for combinations of source acceleration voltage, pre-filters and/or detectors and after measuring the transmission values of several pre-filters, calculating corrected spectra for the combinations of the source acceleration voltage, pre-filters and/or detectors.

Abstract: The present invention provides nanostructures for use in proliferation and differentiation of neural stem cells. The present invention also provides method of proliferating and differentiating neural stem cells.

Abstract: X-ray microscopy tomography scanning systems are not constrained by continuous scanning trajectories like in medical scanners. In fact, the source and detector can be held stationary during subsequent image capture producing a discrete sampling pattern. For such systems, a method of producing an optimized, even illumination of the object by choosing source/detector locations on a surface of an imaginary cylinder surrounding the object is disclosed. The locations, in one example, form a regular lattice with even coverage on the surface of that cylinder, rather than at locations along a continuous curve such as a helix. Using this method, the effective pitch may be increased beyond the theoretical limit imposed by helical scanning, allowing a greater range of y-axis coverage for the same number of projection angles, corresponding to an increase in throughput.

Abstract: X-ray microscopy tomography scanning systems are not constrained by continuous scanning trajectories like in medical scanners. In fact, the source and detector can be held stationary during subsequent image capture producing a discrete sampling pattern. For such systems, a method of producing an optimized, even illumination of the object by choosing source/detector locations on a surface of an imaginary cylinder surrounding the object is disclosed. The locations, in one example, form a regular lattice with even coverage on the surface of that cylinder, rather than at locations along a continuous curve such as a helix. Using this method, the effective pitch may be increased beyond the theoretical limit imposed by helical scanning, allowing a greater range of y-axis coverage for the same number of projection angles, corresponding to an increase in throughput.

Abstract: A segmentation-and-spectrum-based metal artifact reduction (MAR) system and method is applied in polychromatic X-ray CT system that uses a priori knowledge of high-Z metals in samples which contribute the primary artifacts at a known x-ray energy spectrum. Using a basis materials decomposition, the method solves the problem of reducing or eliminating metal artifacts associated with beam hardening using only a single scan of the sample performed at selected x-ray energy.

Abstract: The present invention provides substantia nigra organoids on silica iSECnMs and method of producing the same. The present invention also provides method of cell therapy including the substantia nigra organoids on silica iSECnMs.

Abstract: The present invention provides nanostructures for use in proliferation and differentiation of neural stem cells. The present invention also provides method of proliferating and differentiating neural stem cells.