Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. A method includes: training a neural network having a plurality of network parameters to perform a particular neural network task and to determine trained values of the network parameters using an iterative training process having a plurality of hyperparameters, the method comprising: maintaining a plurality of candidate neural networks and, for each of the candidate neural networks, data specifying: (i) respective values of the network parameters for the candidate neural network, (ii) respective values of the hyperparameters for the candidate neural network, and (iii) a quality measure that measures a performance of the candidate neural network on the particular neural network task; and for each of the plurality of candidate neural networks, repeatedly performing additional training operations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks to predict the structure of a protein.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. A method includes: training a neural network having a plurality of network parameters to perform a particular neural network task and to determine trained values of the network parameters using an iterative training process having a plurality of hyperparameters, the method comprising: maintaining a plurality of candidate neural networks and, for each of the candidate neural networks, data specifying: (i) respective values of the network parameters for the candidate neural network, (ii) respective values of the hyperparameters for the candidate neural network, and (iii) a quality measure that measures a performance of the candidate neural network on the particular neural network task; and for each of the plurality of candidate neural networks, repeatedly performing additional training operations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. A method includes: training a neural network having multiple network parameters to perform a particular neural network task and to determine trained values of the network parameters using an iterative training process having multiple hyperparameters, the method includes: maintaining multiple candidate neural networks and, for each of the multiple candidate neural networks, data specifying: (i) respective values of network parameters for the candidate neural network, (ii) respective values of hyperparameters for the candidate neural network, and (iii) a quality measure that measures a performance of the candidate neural network on the particular neural network task; and for each of the multiple candidate neural networks, repeatedly performing additional training operations.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a predicted structure of a protein that is specified by an amino acid sequence. In one aspect, a method comprises: obtaining a multiple sequence alignment for the protein; determining, from the multiple sequence alignment and for each pair of amino acids in the amino acid sequence of the protein, a respective initial embedding of the pair of amino acids; processing the initial embeddings of the pairs of amino acids using a pair embedding neural network comprising a plurality of self-attention neural network layers to generate a final embedding of each pair of amino acids; and determining the predicted structure of the protein based on the final embedding of each pair of amino acids.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. A method includes: training a neural network having a plurality of network parameters to perform a particular neural network task and to determine trained values of the network parameters using an iterative training process having a plurality of hyperparameters, the method comprising: maintaining a plurality of candidate neural networks and, for each of the candidate neural networks, data specifying: (i) respective values of the network parameters for the candidate neural network, (ii) respective values of the hyperparameters for the candidate neural network, and (iii) a quality measure that measures a performance of the candidate neural network on the particular neural network task; and for each of the plurality of candidate neural networks, repeatedly performing additional training operations.

Abstract: Apparatus (10) for use in MRIS includes a coil arrangement having drive coils (20), shield coils (30) and a power supply unit (PSU) (40). The drive coils (20) and the shield coils (30) are connected in series to the PSU (40) to form a circuit. The shield coils (30) are connected between a first and second length of the drive coils (20) so as to straddle a virtual earth of the circuit. This is advantageous in minimising potential differences within the shield coil (30) assembly and thereby in minimising partial discharge therewithin. Partial discharge between adjacent parts of the drive coils (20) is minimised by spatially arranging those coils (20) such that parts thereof that are at a high electrical potential are spatially adjacent parts thereof that are simultaneously at a potential of the same polarity of at a low electrical potential of either polarity.

Abstract: An electrical coil, particularly a shim coil for use in magnetic resonance imaging spectroscopy, is wound so that there are a plurality of layers with each layer having a plurality of turns. Insulating material is disposed between the turns of each layer. This reduces the capacitance between the turns and has the effect of increasing the self-resonant frequency of the coil. In another embodiment, the coil turn connections are effected so as to divide the overall coil into electrically separated portions and this also increases the self-resonant frequency of the coil.