Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network by estimating the objective function curvature based on current and previous gradients. In one aspect, a method comprises: sampling a batch of training data; and for each neural network parameter: determining, based on the current batch of training data, a respective current gradient of the objective function at the current iteration with respect to the current neural network parameter; estimating an objective function curvature with respect to the current neural network parameter based on (i) the current gradient of the objective function at the current iteration, and (ii) a respective previous gradient of the objective function at each of a plurality of previous iterations; and updating a current value of the neural network parameter based on the estimate of the curvature of the objective function.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for designing a protein by jointly generating an amino acid sequence and a structure of the protein. In one aspect, a method comprises: generating data defining the amino acid sequence and the structure of the protein using a protein design neural network, comprising, for a plurality of positions in the amino acid sequence: receiving the current representation of the protein as of the current position: processing the current representation of the protein using the protein design neural network to generate design data for the current position that comprises: (i) data identifying an amino acid at the current position, and (ii) a set of structure parameters for the current position; and updating the current representation of the protein using the design data for the current position.

Abstract: A reinforcement learning system is proposed comprising a plurality of property detector neural networks. Each property detector neural network is arranged to receive data representing an object within an environment, and to generate property data associated with a property of the object. A processor is arranged to receive an instruction indicating a task associated with an object having an associated property, and process the output of the plurality of property detector neural networks based upon the instruction to generate a relevance data item. The relevance data item indicates objects within the environment associated with the task. The processor also generates a plurality of weights based upon the relevance data item, and, based on the weights, generates modified data representing the plurality of objects within the environment. A neural network is arranged to receive the modified data and to output an action associated with the task.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network by estimating the objective function curvature based on current and previous gradients. In one aspect, a method comprises: sampling a batch of training data; and for each neural network parameter: determining, based on the current batch of training data, a respective current gradient of the objective function at the current iteration with respect to the current neural network parameter; estimating an objective function curvature with respect to the current neural network parameter based on (i) the current gradient of the objective function at the current iteration, and (ii) a respective previous gradient of the objective function at each of a plurality of previous iterations; and updating a current value of the neural network parameter based on the estimate of the curvature of the objective function.

Abstract: A reinforcement learning system is proposed comprising a plurality of property detector neural networks. Each property detector neural network is arranged to receive data representing an object within an environment, and to generate property data associated with a property of the object. A processor is arranged to receive an instruction indicating a task associated with an object having an associated property, and process the output of the plurality of property detector neural networks based upon the instruction to generate a relevance data item. The relevance data item indicates objects within the environment associated with the task. The processor also generates a plurality of weights based upon the relevance data item, and, based on the weights, generates modified data representing the plurality of objects within the environment. A neural network is arranged to receive the modified data and to output an action associated with the task.