Abstract: Techniques for auto-starting a VPN in a MAM environment are disclosed. A MAM-controlled application is launched on a computer system. Policy is queried and a determination is made as to whether to auto-start a VPN application based on the policy. Based on the policy, the VPN application is auto-started, and the VPN application initiates a VPN tunnel that is usable by at least the MAM-controlled application. Network communications transmitted to or from the MAM-controlled application then pass through the VPN tunnel.

Abstract: An authentication method, comprising: obtaining a string; receiving an audio signal; performing speech recognition on the audio signal to extract text; and performing authentication of a user, the authentication comprising: comparing the extracted text and the string; and performing voice authentication of the user based on the audio signal.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection. In one aspect, a method comprises: obtaining: (i) an image, and (ii) a set of one or more query embeddings, wherein each query embedding represents a respective category of object; processing the image and the set of query embeddings using an object detection neural network to generate object detection data for the image, comprising: processing the image using an image encoding subnetwork of the object detection neural network to generate a set of object embeddings; processing each object embedding using a localization subnetwork to generate localization data defining a corresponding region of the image; and processing: (i) the set of object embeddings, and (ii) the set of query embeddings, using a classification subnetwork to generate, for each object embedding, a respective classification score distribution over the set of query embeddings.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object detection. In one aspect, a method comprises: obtaining: (i) an image, and (ii) a set of one or more query embeddings, wherein each query embedding represents a respective category of object; processing the image and the set of query embeddings using an object detection neural network to generate object detection data for the image, comprising: processing the image using an image encoding subnetwork of the object detection neural network to generate a set of object embeddings; processing each object embedding using a localization subnetwork to generate localization data defining a corresponding region of the image; and processing: (i) the set of object embeddings, and (ii) the set of query embeddings, using a classification subnetwork to generate, for each object embedding, a respective classification score distribution over the set of query embeddings.

Abstract: Generally, the present disclosure is directed to systems and methods that provide a simple, scalable, yet effective strategy to perform transfer learning with a mixture of experts (MoE). In particular, the transfer of pre-trained representations can improve sample efficiency and reduce computational requirements for new tasks. However, representations used for transfer are usually generic, and are not tailored to a particular distribution of downstream tasks. In contrast, example systems and methods of the present disclosure use expert representations for transfer with a simple, yet effective, strategy.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more expert neural network blocks that each include multiple routers and multiple expert neural networks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training Vision Transformer (ViT) neural networks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using mixer neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more mixer neural network layers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to perform a downstream computer vision task. One of the methods includes pre-training an initial neural network that shares layers with the neural network to perform an initial computer vision task and then training the neural network on the downstream computer vision task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training neural networks using transfer learning.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes receiving training data for training a task neural network to perform a particular machine learning task; and selecting, from a space of possible architectures, an architecture for the task neural network, wherein the space of possible architectures is represented as a graph of nodes connected by edges, each node in the graph representing a decision point in selecting the architecture and each edge in the graph representing an action.

Abstract: The present invention relates to methods for repairing a structural weakness in an aircraft fuselage, or preventing the advancement of a structural weakness in an aircraft fuselage. Cold spray methods such as supersonic particle deposition have been shown to positively affect structural characteristics of sheet metal and lap joints as used in fuselage construction.

Abstract: This invention relates to the preparation of nucleic acid samples for analysis. The invention may be particularly useful for single stranded samples. Embodiments of the invention involve the attachment of double stranded or hairpin oligonucleotides using template independent polymerase enzymes in the preparation of nucleic acid sequencing libraries.

Abstract: This invention relates to the preparation of nucleic acid samples for analysis. The invention may be particularly useful for single stranded samples. Embodiments of the invention involve the attachment of double stranded or hairpin oligonucleotides using template independent polymerase enzymes in the preparation of nucleic acid sequencing libraries.

Abstract: This invention relates to improved methods and kits for identification of 5-formylcytosine (5fC) to be distinguished from cytosine (C) in a sample nucleotide sequence. Methods comprise reducing a first portion of polynucleotides which comprise the sample nucleotide sequence; treating the reduced first portion and a second portion of polynucleotides with bisulfite; sequencing the polynucleotides in the first and second portions of the population to produce first and second nucleotide sequences respectively and; identifying the residues in the first and second nucleotide sequences which correspond to a cytosine residue in the sample nucleotide sequence. These methods may be useful, for example in the analysis of genomic DNA and/or of RNA.

Abstract: A method is provided for repairing a structural weakness, preventing or inhibiting the initiation of a structural weakness, or preventing or inhibiting the progression of a structural weakness in an aircraft frame element. The method includes bonding a plurality of particles to the element such that the plurality of metallic particles form a continuous layer over the area of weakness, or the predicted area of weakness. The metallic particles may be applied by a cold spray process such as supersonic particle deposition.

Abstract: This invention relates to the preparation of nucleic acid samples for analysis. The invention may be particularly useful for single stranded samples. Embodiments of the invention involve the attachment of double stranded or hairpin oligonucleotides using template independent polymerase enzymes in the preparation of nucleic acid sequencing libraries.

Abstract: The present invention relates to methods for repairing a structural weakness in an aircraft fuselage, or preventing the advancement of a structural weakness in an aircraft fuselage. Cold spray methods such as supersonic particle deposition have been shown to positively affect structural characteristics of sheet metal and lap joints as used in fuselage construction.