Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.

Abstract: Example embodiments of the present disclosure relate to systems and methods for compressing attributes of volumetric and hypervolumetric datasets. An example system performs operations including obtaining a reference dataset comprising attributes indexed by a domain of multidimensional coordinates; subdividing the domain into a plurality of blocks respectively associated with a plurality of attribute subsets; inputting, to a local nonlinear operator, a latent representation for an attribute subset associated with at least one block of the plurality of blocks; obtaining, using the local nonlinear operator and based on the latent representation, an attribute representation of one or more attributes of the attribute subset; and updating the latent representation based on a comparison of the attribute representation and the reference dataset.

Abstract: Example embodiments of the present disclosure relate to systems and methods for compressing attributes of volumetric and hypervolumetric datasets. An example system performs operations including obtaining a reference dataset comprising attributes indexed by a domain of multidimensional coordinates; subdividing the domain into a plurality of blocks respectively associated with a plurality of attribute subsets; inputting, to a local nonlinear operator, a latent representation for an attribute subset associated with at least one block of the plurality of blocks; obtaining, using the local nonlinear operator and based on the latent representation, an attribute representation of one or more attributes of the attribute subset; and updating the latent representation based on a comparison of the attribute representation and the reference dataset.

Abstract: Example embodiments of the present disclosure relate to systems and methods for compressing attributes of volumetric and hypervolumetric datasets. An example system performs operations including obtaining a reference dataset comprising attributes indexed by a domain of multidimensional coordinates; subdividing the domain into a plurality of blocks respectively associated with a plurality of attribute subsets; inputting, to a local nonlinear operator, a latent representation for an attribute subset associated with at least one block of the plurality of blocks; obtaining, using the local nonlinear operator and based on the latent representation, an attribute representation of one or more attributes of the attribute subset; and updating the latent representation based on a comparison of the attribute representation and the reference dataset.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.

Abstract: An encoder system can include a pixel grid generator to receive an image having a first dimension, generate a grid having a second dimension, add a plurality of points to positions on the grid, and map a plurality of pixels of the image to the plurality of points. The encoder system can include a color module to assign a color to each of the plurality of points using a color table, a triangulation module to generate a plurality of vertices based on the plurality of points and triangulate the grid using the vertices, and a compression module to compress the vertices as a set of compressed vertex positions and a set of vertex colors.

Abstract: An encoder system can include a pixel grid generator to receive an image having a first dimension, generate a grid having a second dimension, add a plurality of points to positions on the grid, and map a plurality of pixels of the image to the plurality of points. The encoder system can include a color module to assign a color to each of the plurality of points using a color table, a triangulation module to generate a plurality of vertices based on the plurality of points and triangulate the grid using the vertices, and a compression module to compress the vertices as a set of compressed vertex positions and a set of vertex colors.

Abstract: A mat assembly is provided for absorbing liquid, such as oil, that may be spilled near a machine or automotive vehicle. The mat assembly includes a mat with at least an upper layer formed from a woven or non-woven array of fibers. The mat assembly further includes a frame formed from strips that can be cut to match the periphery of the mat. Each strip has a bottom surface with an attachment tape that can be engaged releasably with the woven or non-woven fibers of the mat. The restraining strip may include an array of resilient hooked filaments that can engage the fibers of the mat. The strips hold the mat in a planar orientation. However, the strips can be separated from the mat easily when the mat has become saturated. The mat then can be discarded and replaced with a new mat, and the same strips can be fixed to the upper surface of the new mat.

Abstract: A mat assembly is provided for absorbing liquid, such as oil, that may be spilled near a machine or automotive vehicle. The mat assembly includes a mat with at least an upper layer formed from a woven or non-woven array of fibers. The mat assembly further includes a frame formed from strips that can be cut to match the periphery of the mat. Each strip has a bottom surface with an attachment tape that can be engaged releasably with the woven or non-woven fibers of the mat. The restraining strip may include an array of resilient hooked filaments that can engage the fibers of the mat. The strips hold the mat in a planar orientation. However, the strips can be separated from the mat easily when the mat has become saturated. The mat then can be discarded and replaced with a new mat, and the same strips can be fixed to the upper surface of the new mat.

Abstract: A barrier assembly is provided for protecting shorelines and structures adjacent shorelines from damage attributable to oil spills. The barrier assembly includes a flexible sheet material that is impermeable to oil. One surface of the flexible sheet material may also have oil-absorbing characteristics. Each sheet has a top edge from which tie downs extend for securing sheets to structures adjacent the shoreline. Each sheet also includes a bottom edge having anchors for holding the bottom edge below the surface of the water. The sheets may include structure for connecting adjacent sheets in top-to-bottom relationship and/or in side-to-side relationship.

Abstract: A nonwoven fabric comprising at least one layer of textile fibers or net of polymeric filaments and at least one web of melt blown microfibers, bonded together by hydroentangling. The nonwoven fabric may be apertured by hydroentangling or may have areas of higher density and areas of lower density. The fabric has a favorable combination of softness, dryness, tensile strength and hand. Several processes are provided for producing the nonwoven fabric of the invention.