Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for compressing and decompressing data signals using sparse, meta-learned neural networks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scalable continual learning using neural networks. One of the methods includes receiving new training data for a new machine learning task; training an active subnetwork on the new training data to determine trained values of the active network parameters from initial values of the active network parameters while holding current values of the knowledge parameters fixed; and training a knowledge subnetwork on the new training data to determine updated values of the knowledge parameters from the current values of the knowledge parameters by training the knowledge subnetwork to generate knowledge outputs for the new training inputs that match active outputs generated by the trained active subnetwork for the new training inputs.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scalable continual learning using neural networks. One of the methods includes receiving new training data for a new machine learning task; training an active subnetwork on the new training data to determine trained values of the active network parameters from initial values of the active network parameters while holding current values of the knowledge parameters fixed; and training a knowledge subnetwork on the new training data to determine updated values of the knowledge parameters from the current values of the knowledge parameters by training the knowledge subnetwork to generate knowledge outputs for the new training inputs that match active outputs generated by the trained active subnetwork for the new training inputs.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scalable continual learning using neural networks. One of the methods includes receiving new training data for a new machine learning task; training an active subnetwork on the new training data to determine trained values of the active network parameters from initial values of the active network parameters while holding current values of the knowledge parameters fixed; and training a knowledge subnetwork on the new training data to determine updated values of the knowledge parameters from the current values of the knowledge parameters by training the knowledge subnetwork to generate knowledge outputs for the new training inputs that match active outputs generated by the trained active subnetwork for the new training inputs.

Abstract: A fuel savings informational system is provided for implementation on an alternative fuel vehicle the operation of which may be characterized by a first plurality of fixed parameters and a second plurality of variable parameters. The system compares the fuel consumption of the alternative fuel vehicle to that of a virtual comparison vehicle characterized by a third plurality of fixed parameters, and comprises a plurality of sensors for monitoring the second plurality and a processor coupled thereto. The processor is configured to recall the first and third pluralities, capture data corresponding to the second plurality, and determine the fuel consumption of the alternative fuel vehicle from the second plurality. The processor is further configured to estimate the fuel consumption of the comparison vehicle from the first, second, and third pluralities, and compare the fuel consumption of the alternative fuel vehicle to the estimated fuel consumption of the comparison vehicle.