Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

Abstract: A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.

Abstract: Systems and methods for classifying an image using a machine learning model. One of the methods includes obtaining training data for training the machine learning model, wherein the machine learning model is configured to process input images to generate, for each input image, a predicted point in an embedding space; determining, from label data for training images in the training data, a respective numeric embedding of each of the object categories, wherein a distance in the embedding space between the numeric embeddings of any two object categories reflects a degree of visual co-occurrence of the two object categories; and training the machine learning model on the training data. The systems described in this specification can effectively perform multi-label, massively multi-category image classification, where the number of classes is large (many thousands or tens of thousands) and where each image typically belongs to multiple categories that should all be properly identified.

Abstract: The invention relates to the use of zeolites for supplying plants with micronutrients that can be assimilated, in particular using a composition including a zeolite and a micronutrient. The invention mainly pertains to the field of agriculture, in particular to the prevention or correction of assessed micronutrient deficiencies in plants grown in open fields or through hydroponics.

Abstract: This invention relates to a silicate-containing flame-resistant adhesive composition comprising an inorganic component consisting, with respect to the weight of the total composition, of (a) 20-90wt% of a concentrated aqueous alkali metal silicate solution, (b) 5-25wt% of a clay and 2-7wt% of deflocculated asbestos fibres; and (2) an organic component present as a 30-70% aqueous solution of a carboxymethylcellulose, a starch ether, a dextrin or mixtures thereof, this organic component being present in an amount (dry weight) of 0.2-2wt% by weight of the total composition. The composition may be prepared by (A) charging the silicate solution in a container and rotating same in a given direction, (B) intimately dispersing the aqueous organic component solution while rotating same in the opposite direction, (C) adding the clay on completion of the dispersion, with continued stirring and (D) then dispersing the deflocculated asbestos fibres in the stirred mixture.