Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

Abstract: A method includes, responsive to receiving a modified first reservation command from a storage controller, identifying, by a storage drive, a first range of storage based on a first range identifier of the modified reservation command. The method also includes granting, by the storage drive, a reservation for access to the storage drive on behalf of a first host controller by associating the reservation for the first range with a second range of storage.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for predicting an exchange-correlation energy of an atomic system. The system obtains respective electron-orbital features of the atomic system at each of a plurality of grid points; generates, for each of the plurality of grid points, a respective input feature vector for the electron-orbital features at the grid point; and processes the respective input feature vectors for the plurality of grid points using a neural network to generate a predicted exchange-correlation energy of the atomic system.

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

Abstract: A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and shared module are trained on a plurality of different tasks, such that each worker learns to perform a corresponding one of the tasks according to a respective task policy, and said shared policy network learns a multitask policy which represents common behavior for the tasks. The coordinated training is performed by optimizing an objective function comprising, for each task: a reward term indicative of an expected reward earned by a worker in performing the corresponding task according to the task policy; and at least one entropy term which regularizes the distribution of the task policy towards the distribution of the multitask policy.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises generating a distance map for a given protein, wherein the given protein is defined by a sequence of amino acid residues arranged in a structure, wherein the distance map characterizes estimated distances between the amino acid residues in the structure, comprising: generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein the first positions are a proper subset of the sequence; and generating the distance map for the given protein using the plurality of distance map crops.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for predicting one or more properties of a material. One of the methods includes maintaining data specifying a set of known materials each having a respective known physical structure; receiving data specifying a new material; identifying a plurality of known materials in the set of known materials that are similar to the new material; determining a predicted embedding of the new material from at least respective embeddings corresponding to each of the similar known materials; and processing the predicted embedding of the new material using an experimental prediction neural network to predict one or more properties of the new material.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction and protein domain segmentation. In one aspect, a method comprises generating a plurality of predicted structures of a protein, wherein generating a predicted structure of the protein comprises: updating initial values of a plurality of structure parameters of the protein, comprising, at each of a plurality of update iterations: determining a gradient of a quality score for the current values of the structure parameters with respect to the current values of the structure parameters; and updating the current values of the structure parameters using the gradient.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises, at each of one or more iterations: determining an alternative predicted structure of a given protein defined by alternative values of structure parameters; processing, using a geometry neural network, a network input comprising: (i) a representation of a sequence of amino acid residues in the given protein, and (ii) the alternative values of the structure parameters, to generate an output characterizing an alternative geometry score that is an estimate of a similarity measure between the alternative predicted structure and the actual structure of the given protein.

Abstract: A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and shared module are trained on a plurality of different tasks, such that each worker learns to perform a corresponding one of the tasks according to a respective task policy, and said shared policy network learns a multitask policy which represents common behavior for the tasks. The coordinated training is performed by optimizing an objective function comprising, for each task: a reward term indicative of an expected reward earned by a worker in performing the corresponding task according to the task policy; and at least one entropy term which regularizes the distribution of the task policy towards the distribution of the multitask policy.

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

Abstract: A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and shared module are trained on a plurality of different tasks, such that each worker learns to perform a corresponding one of the tasks according to a respective task policy, and said shared policy network learns a multitask policy which represents common behavior for the tasks. The coordinated training is performed by optimizing an objective function comprising, for each task: a reward term indicative of an expected reward earned by a worker in performing the corresponding task according to the task policy; and at least one entropy term which regularizes the distribution of the task policy towards the distribution of the multitask policy.

Abstract: A vacuum cleaner comprises a housing and a motor fan assembly arranged to generate an air flow. A detachable dirt container is mountable to the housing and the dirt container has a dirty air inlet in fluid communication with the motor fan assembly. A filter is for separating dirt from the air flow and the filter is mounted between the dirt container and the motor fan assembly. Wherein the detachable dirt container comprises an emptying aperture in a wall of the dirt container, the emptying aperture being downstream in the air flow from the dirty air inlet and upstream of the filter. Wherein the housing comprises an overlap portion for covering the emptying aperture in the dirt container and sealing the emptying aperture when the detachable dirt container is mounted to the housing.

Abstract: A method of training a machine learning model having multiple parameters, in which the machine learning model has been trained on a first machine learning task to determine first values of the parameters of the machine learning model.

Abstract: A vacuum cleaner comprises a housing and a motor fan assembly arranged to generate an air flow. A detachable dirt container is mountable to the housing and the dirt container has a dirty air inlet in fluid communication with the motor fan assembly. A filter is for separating dirt from the air flow and the filter is mounted between the dirt container and the motor fan assembly. Wherein the detachable dirt container comprises an emptying aperture in a wall of the dirt container, the emptying aperture being downstream in the air flow from the dirty air inlet and upstream of the filter. Wherein the housing comprises an overlap portion for covering the emptying aperture in the dirt container and sealing the emptying aperture when the detachable dirt container is mounted to the housing.

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.

Abstract: The present invention relates to a method for the early diagnosis of a clinically latent placental insufficiency in pathological placental maturation, and the prophylaxis of an intrauterine fetal hypoxia/asphyxia at the due date or after a prolonged gestation, comprising determining the amount and/or the concentration of the biomarker prokineticin 1 (EG-VEGF) and/or its receptor PKR1 and/or PKR2 in a sample from the pregnant subject and/or the pregnancy. In a preferred embodiment, the invention is based on determining the ratio of the amount and/or the concentration of bFGF/PK1 as a measure of current functional condition and an indicator of latent clinical problems such as placental dysfunction resulting in fetal hypoxia.

Abstract: The present invention relates to a method for the early diagnosis of a clinically latent placental insufficiency in pathological placental maturation, and the prophylaxis of an intrauterine fetal hypoxia/asphyxia at the due date or after a prolonged gestation, comprising determining the amount and/or the concentration of the biomarker prokineticin 1 (EG-VEGF) and/or its receptor PKR1 and/or PKR2 in a sample from the pregnant subject and/or the pregnancy. In a preferred embodiment, the invention is based on determining the ratio of the amount and/or the concentration of bFGF/PK1 as a measure of current functional condition and an indicator of latent clinical problems such as placental dysfunction resulting in fetal hypoxia.

Abstract: In accordance with one aspect of the disclosed technology, wireless communications are used in a fiber surveillance system to enable monitoring of remote locations for vibrations, acoustic signals, stresses, stress fatigue or other detectable characteristics. A fiber that is deployed in the structure or region being monitored is connected a wireless transmitter that is used to transmit, to a receiving system, return optical signals obtained with the surveillance system. The return signals can be transmitted in raw form or after partial or total analysis.