Abstract: A method and system for training a model for image generation. The model includes a hybrid variational auto-encoder (VAE)—generative adversarial network (GAN) framework. The method includes the steps of: multiple input of an input image into the VAE which outputs in response multiple distinct output image samples, determining the best of the multiple output image samples as a best-of-many sample, the best-of-many sample having the minimum reconstruction cost, and training the model based on a predefined training objective, the predefined training objective integrating the best-of-many sample reconstruction cost and a GAN-based synthetic likelihood term.

Abstract: A method for training a model to be used for processing images, wherein the model comprises: —a first portion (101) configured to receive images as input and configured to output a feature map, —a second portion (102) configured to receive the feature map outputted by the first portion as input and configured to output a semantic segmentation, the method comprising: —training a generator (201) so that the generator is configured to generate a feature map configured to be used as input to the second portion, —generating a plurality of feature maps using the generator, —training the second portion using the feature maps generated by the generator.

Abstract: A shredding device is provided comprising two shredding shafts arranged parallel to each other with shredding elements arranged thereon, wherein the shredding shafts are preferably rotatable mechanically synchronized to each other. A shaft-side coupling element is connected to a respective first end of the shredding shafts. The shredding device includes a housing with a housing-side coupling element is provided that can be coupled to the shaft-side coupling element. The shredding device includes a displacement device enabling displacement of the shredding shafts for decoupling and coupling the shaft-side coupling element from or to the housing-side coupling element.

Abstract: A shredding device is provided comprising two shredding shafts arranged parallel to each other with shredding elements arranged thereon, wherein the shredding shafts are preferably rotatable mechanically synchronized to each other. A shaft-side coupling element is connected to a respective first end of the shredding shafts. The shredding device includes a housing with a housing-side coupling element is provided that can be coupled to the shaft-side coupling element. The shredding device includes a displacement device enabling displacement of the shredding shafts for decoupling and coupling the shaft-side coupling element from or to the housing-side coupling element.

Abstract: A method for producing a machine casing of a shredding device includes providing component parts and/or assembly groups of the machine casing of the shredding device. Retaining ring bolts are provided, and at least some of the component parts and/or assembly groups of the machine casing are connected to each other through use of the retaining bolt rings.

Abstract: A device for comminuting material components includes a housing, at least one rotor that is supported in the housing and has rotor blades and rotor teeth mounted thereon, at least one stator blade that can be supported on the housing, and at least one screen device, which can be moved from an operational state of the comminuting device downward or laterally relative to the housing to a maintenance state, wherein in the operational state the at least one stator blade and the at least one screen device are supported against each other and can be moved together into the maintenance state.

Abstract: Methods for recognizing a category of an object are disclosed. In one embodiment, a method includes determining, by a processor, a preliminary category of a target object, the preliminary category having a confidence score associated therewith, and comparing the confidence score to a learning threshold. If the highest confidence score is less than the learning threshold, the method further includes estimating properties of the target object and generating a property score for one or more estimated properties, and searching a supplemental image collection for supplemental image data using the preliminary category and the one or more estimated properties. Robots programmed to recognize a category of an object by use of supplemental image data are also disclosed.

Abstract: The present invention relates to fastening means for fastening a screen plate onto a screen carrier of a screen device for a comminuting device, comprising a first tensioning element, which is connected to the screen device, particularly to the screen carrier, and which is designed to exert a force on the screen plate; a second tensioning element, which is connected to the screen device, particularly the screen carrier, and which is designed to exert a force on the screen plate, wherein at least one of the tensioning elements is an elastic element, which is designed to exert an elastic restoring force on the screen plate such that the screen plate is tensioned between the first and the second tensioning elements. The invention further relates to a method for fastening a screen plate onto a screen carrier of a screen device for a comminuting device.

Abstract: Methods for recognizing a category of an object are disclosed. In one embodiment, a method includes determining, by a processor, a preliminary category of a target object, the preliminary category having a confidence score associated therewith, and comparing the confidence score to a learning threshold. If the highest confidence score is less than the learning threshold, the method further includes estimating properties of the target object and generating a property score for one or more estimated properties, and searching a supplemental image collection for supplemental image data using the preliminary category and the one or more estimated properties. Robots programmed to recognize a category of an object by use of supplemental image data are also disclosed.

Abstract: The present invention relates to a method for producing a machine casing of a shredding device, comprising the steps of providing component parts and/or assembly groups of the machine casing of the shredding device; providing retaining ring bots; and connecting at least some of the component parts and/or assembly groups of the machine casing to each other by means of the retaining bolt rings.

Abstract: The present invention relates to a device for comminuting material components. The invention comprises a housing, at least one rotor (1) that is supported in the housing and has rotor blades (2) and rotor teeth mounted thereon, at least one stator blade (3) that can be supported on the housing, and at least one screen device (4), which can be moved from an operational state of the comminuting device downward or laterally relative to the housing to a maintenance state, wherein in the operational state the at least one stator blade (3) and the at least one screen device (4) are supported against each other and can be moved together into the maintenance state.

Abstract: The present invention relates to fastening means for fastening a screen plate onto a screen carrier of a screen device for a comminuting device, comprising a first tensioning element, which is connected to the screen device, particularly to the screen carrier, and which is designed to exert a force on the screen plate; a second tensioning element, which is connected to the screen device, particularly the screen carrier, and which is designed to exert a force on the screen plate, wherein at least one of the tensioning elements is an elastic element, which is designed to exert an elastic restoring force on the screen plate such that the screen plate is tensioned between the first and the second tensioning elements. The invention further relates to a method for fastening a screen plate onto a screen carrier of a screen device for a comminuting device.