Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable media, for obtaining, from a first sensor, first sensor data corresponding to an object, wherein the first sensor data is of a first modality; providing the first sensor data to a trained neural network; and generating second sensor data corresponding to the object based at least on an output of the trained neural network, wherein the second sensor data is of a second modality that is different than the first modality.

Abstract: Methods and apparatuses are described for conducting cross-blockchain currency transactions. A server receives, from a client device, a request for a conversion of an amount of a first currency to an amount of a second currency. The amount of the first currency is stored in an electronic wallet associated with a user of the client device. The server determines one or more sequences of currency transactions executable that achieves the conversion from the amount of the first currency to the amount of the second currency, the one or more sequences of currency transactions comprising converting between cryptocurrencies operating on different blockchains. The server identifies one of the one or more sequences of currency transactions associated with an optimal value. The server executes the identified sequence of currency transactions associated with the optimal value.